someaistuff.

Benchmark explorer.

LiveBench Design2.0 · 2026-10-14 (dataset 2026-09-02) · Higher is better
Source ↗
Method

Single-run mean task score, 0–100.

Score × cost

Where performance meets price

LiveBench Design · 1M input + 250K output tokens · uncached USD

21 priced resultsPareto frontier
Anthropic: Claude Opus 5.5 ↗86.9% LiveBench Design · $9.00 workload · Amazon Bedrock · via OpenRouter

Evaluation: Effort: max · single run. Price: $4.00 input / $20.00 output per 1M tokens · amazon-bedrock.

LiveBench Design score versus workload cost40%60%80%100%$0.01$0.10$1$10$100Higher score is betterWorkload cost · USD · log scaleNVIDIA: Nemotron 3.5 Lightning · 43.9% LiveBench Design · $0.055 workload · Darkbloom · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.025 input / $0.12 output per 1M tokens · darkbloom/int4 · quantization=int4.OpenAI: GPT-6 Luna · 82.5% LiveBench Design · $0.1125 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.05 input / $0.25 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.DeepSeek: DeepSeek V4.1 Flash · 77% LiveBench Design · $0.135 workload · Decart · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.09 input / $0.18 output per 1M tokens · decart/fp4 · quantization=fp4.GLM-5.3-Flash · 77.2% LiveBench Design · $0.1375 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.075 input / $0.25 output per 1M tokens · deepinfra/fp4 · quantization=fp4.Qwen3.8-27B · 75.9% LiveBench Design · $0.145 workload · Tenstorrent · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.02 input / $0.50 output per 1M tokens · tenstorrent/fp4 · quantization=fp4.Google: Gemma 4 31B · 58.4% LiveBench Design · $0.185 workload · CoreWeave · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.10 input / $0.34 output per 1M tokens · coreweave/fp4 · quantization=fp4.Qwen: Qwen3.8 Flash · 72.8% LiveBench Design · $0.2675 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.15 input / $0.47 output per 1M tokens · alibaba/us-east-1.DeepSeek-V4-Flash-Vision-Exp · 70.7% LiveBench Design · $0.3773 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.2156 input / $0.6468 output per 1M tokens · deepinfra/fp8 · quantization=fp8.Reflection: Beam 1.0 501B A23B · 67.9% LiveBench Design · $0.50 workload · Nebius · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.25 input / $1.00 output per 1M tokens · nebius/fp8 · quantization=fp8.Xiaomi: MiMo-V2.6-Pro · 78.5% LiveBench Design · $0.6475 workload · DeepInfra · via OpenRouter · Evaluation: Effort: high · single run. Price: $0.43 input / $0.87 output per 1M tokens · deepinfra/fp8 · quantization=fp8.GLM-5.3 · 77.3% LiveBench Design · $0.8763 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.50 input / $1.505 output per 1M tokens · sail-research/us · quantization=fp8.Step-5-Preview · 76.9% LiveBench Design · $1.675 workload · DeepInfra · Evaluation: Effort: max · single run. Price: $1.00 input / $2.70 output per 1M tokens.OpenAI: GPT-6.1 Sol · 82.1% LiveBench Design · $2.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $1.00 input / $5.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.Google: Gemini 4 Argon · 73.7% LiveBench Design · $2.25 workload · Google AI Studio · via OpenRouter · Evaluation: Effort: high · single run. Price: $1.00 input / $5.00 output per 1M tokens · google-ai-studio/flex · tier=flex.Meta: Muse Spark Open · 60.3% LiveBench Design · $2.3125 workload · baseten · via Hugging Face · Evaluation: Effort: max · single run. Price: $1.25 input / $4.25 output per 1M tokens.Kimi-K3 · 77.2% LiveBench Design · $2.529 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.504 input / $8.10 output per 1M tokens · sail-research/fp4 · quantization=fp4.Qwen: Qwen3.8 2.4T A95B · 78.6% LiveBench Design · $3.50 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $6.00 output per 1M tokens · alibaba.Anthropic: Claude Sonnet 5.5 · 85% LiveBench Design · $4.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $10.00 output per 1M tokens · amazon-bedrock.Anthropic: Claude Opus 5.5 · 86.9% LiveBench Design · $9.00 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $4.00 input / $20.00 output per 1M tokens · amazon-bedrock.OpenAI: GPT-6 Astra · 82% LiveBench Design · $11.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $5.00 input / $25.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.Anthropic: Claude Fable 5.1 · 83.4% LiveBench Design · $22.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $10.00 input / $50.00 output per 1M tokens · amazon-bedrock.NVIDIA: Nemotron 3.5 Lightning · 43.9% LiveBench Design · $0.055 workload · Darkbloom · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.025 input / $0.12 output per 1M tokens · darkbloom/int4 · quantization=int4.1OpenAI: GPT-6 Luna · 82.5% LiveBench Design · $0.1125 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.05 input / $0.25 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.2DeepSeek: DeepSeek V4.1 Flash · 77% LiveBench Design · $0.135 workload · Decart · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.09 input / $0.18 output per 1M tokens · decart/fp4 · quantization=fp4.3GLM-5.3-Flash · 77.2% LiveBench Design · $0.1375 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.075 input / $0.25 output per 1M tokens · deepinfra/fp4 · quantization=fp4.4Qwen3.8-27B · 75.9% LiveBench Design · $0.145 workload · Tenstorrent · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.02 input / $0.50 output per 1M tokens · tenstorrent/fp4 · quantization=fp4.5Google: Gemma 4 31B · 58.4% LiveBench Design · $0.185 workload · CoreWeave · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.10 input / $0.34 output per 1M tokens · coreweave/fp4 · quantization=fp4.6Qwen: Qwen3.8 Flash · 72.8% LiveBench Design · $0.2675 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.15 input / $0.47 output per 1M tokens · alibaba/us-east-1.7DeepSeek-V4-Flash-Vision-Exp · 70.7% LiveBench Design · $0.3773 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.2156 input / $0.6468 output per 1M tokens · deepinfra/fp8 · quantization=fp8.8Reflection: Beam 1.0 501B A23B · 67.9% LiveBench Design · $0.50 workload · Nebius · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.25 input / $1.00 output per 1M tokens · nebius/fp8 · quantization=fp8.9Xiaomi: MiMo-V2.6-Pro · 78.5% LiveBench Design · $0.6475 workload · DeepInfra · via OpenRouter · Evaluation: Effort: high · single run. Price: $0.43 input / $0.87 output per 1M tokens · deepinfra/fp8 · quantization=fp8.10GLM-5.3 · 77.3% LiveBench Design · $0.8763 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.50 input / $1.505 output per 1M tokens · sail-research/us · quantization=fp8.11Step-5-Preview · 76.9% LiveBench Design · $1.675 workload · DeepInfra · Evaluation: Effort: max · single run. Price: $1.00 input / $2.70 output per 1M tokens.12OpenAI: GPT-6.1 Sol · 82.1% LiveBench Design · $2.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $1.00 input / $5.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.13Google: Gemini 4 Argon · 73.7% LiveBench Design · $2.25 workload · Google AI Studio · via OpenRouter · Evaluation: Effort: high · single run. Price: $1.00 input / $5.00 output per 1M tokens · google-ai-studio/flex · tier=flex.14Meta: Muse Spark Open · 60.3% LiveBench Design · $2.3125 workload · baseten · via Hugging Face · Evaluation: Effort: max · single run. Price: $1.25 input / $4.25 output per 1M tokens.15Kimi-K3 · 77.2% LiveBench Design · $2.529 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.504 input / $8.10 output per 1M tokens · sail-research/fp4 · quantization=fp4.16Qwen: Qwen3.8 2.4T A95B · 78.6% LiveBench Design · $3.50 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $6.00 output per 1M tokens · alibaba.17Anthropic: Claude Sonnet 5.5 · 85% LiveBench Design · $4.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $10.00 output per 1M tokens · amazon-bedrock.18Anthropic: Claude Opus 5.5 · 86.9% LiveBench Design · $9.00 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $4.00 input / $20.00 output per 1M tokens · amazon-bedrock.19OpenAI: GPT-6 Astra · 82% LiveBench Design · $11.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $5.00 input / $25.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.20Anthropic: Claude Fable 5.1 · 83.4% LiveBench Design · $22.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $10.00 input / $50.00 output per 1M tokens · amazon-bedrock.21LiveBench Design score versus workload cost40%60%80%100%$0.01$0.10$1$10$100Higher score is betterWorkload cost · USD · log scaleNVIDIA: Nemotron 3.5 Lightning · 43.9% LiveBench Design · $0.055 workload · Darkbloom · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.025 input / $0.12 output per 1M tokens · darkbloom/int4 · quantization=int4.OpenAI: GPT-6 Luna · 82.5% LiveBench Design · $0.1125 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.05 input / $0.25 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.DeepSeek: DeepSeek V4.1 Flash · 77% LiveBench Design · $0.135 workload · Decart · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.09 input / $0.18 output per 1M tokens · decart/fp4 · quantization=fp4.GLM-5.3-Flash · 77.2% LiveBench Design · $0.1375 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.075 input / $0.25 output per 1M tokens · deepinfra/fp4 · quantization=fp4.Qwen3.8-27B · 75.9% LiveBench Design · $0.145 workload · Tenstorrent · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.02 input / $0.50 output per 1M tokens · tenstorrent/fp4 · quantization=fp4.Google: Gemma 4 31B · 58.4% LiveBench Design · $0.185 workload · CoreWeave · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.10 input / $0.34 output per 1M tokens · coreweave/fp4 · quantization=fp4.Qwen: Qwen3.8 Flash · 72.8% LiveBench Design · $0.2675 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.15 input / $0.47 output per 1M tokens · alibaba/us-east-1.DeepSeek-V4-Flash-Vision-Exp · 70.7% LiveBench Design · $0.3773 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.2156 input / $0.6468 output per 1M tokens · deepinfra/fp8 · quantization=fp8.Reflection: Beam 1.0 501B A23B · 67.9% LiveBench Design · $0.50 workload · Nebius · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.25 input / $1.00 output per 1M tokens · nebius/fp8 · quantization=fp8.Xiaomi: MiMo-V2.6-Pro · 78.5% LiveBench Design · $0.6475 workload · DeepInfra · via OpenRouter · Evaluation: Effort: high · single run. Price: $0.43 input / $0.87 output per 1M tokens · deepinfra/fp8 · quantization=fp8.GLM-5.3 · 77.3% LiveBench Design · $0.8763 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.50 input / $1.505 output per 1M tokens · sail-research/us · quantization=fp8.Step-5-Preview · 76.9% LiveBench Design · $1.675 workload · DeepInfra · Evaluation: Effort: max · single run. Price: $1.00 input / $2.70 output per 1M tokens.OpenAI: GPT-6.1 Sol · 82.1% LiveBench Design · $2.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $1.00 input / $5.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.Google: Gemini 4 Argon · 73.7% LiveBench Design · $2.25 workload · Google AI Studio · via OpenRouter · Evaluation: Effort: high · single run. Price: $1.00 input / $5.00 output per 1M tokens · google-ai-studio/flex · tier=flex.Meta: Muse Spark Open · 60.3% LiveBench Design · $2.3125 workload · baseten · via Hugging Face · Evaluation: Effort: max · single run. Price: $1.25 input / $4.25 output per 1M tokens.Kimi-K3 · 77.2% LiveBench Design · $2.529 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.504 input / $8.10 output per 1M tokens · sail-research/fp4 · quantization=fp4.Qwen: Qwen3.8 2.4T A95B · 78.6% LiveBench Design · $3.50 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $6.00 output per 1M tokens · alibaba.Anthropic: Claude Sonnet 5.5 · 85% LiveBench Design · $4.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $10.00 output per 1M tokens · amazon-bedrock.Anthropic: Claude Opus 5.5 · 86.9% LiveBench Design · $9.00 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $4.00 input / $20.00 output per 1M tokens · amazon-bedrock.OpenAI: GPT-6 Astra · 82% LiveBench Design · $11.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $5.00 input / $25.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.Anthropic: Claude Fable 5.1 · 83.4% LiveBench Design · $22.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $10.00 input / $50.00 output per 1M tokens · amazon-bedrock.NVIDIA: Nemotron 3.5 Lightning · 43.9% LiveBench Design · $0.055 workload · Darkbloom · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.025 input / $0.12 output per 1M tokens · darkbloom/int4 · quantization=int4.1OpenAI: GPT-6 Luna · 82.5% LiveBench Design · $0.1125 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.05 input / $0.25 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.2DeepSeek: DeepSeek V4.1 Flash · 77% LiveBench Design · $0.135 workload · Decart · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.09 input / $0.18 output per 1M tokens · decart/fp4 · quantization=fp4.3GLM-5.3-Flash · 77.2% LiveBench Design · $0.1375 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.075 input / $0.25 output per 1M tokens · deepinfra/fp4 · quantization=fp4.4Qwen3.8-27B · 75.9% LiveBench Design · $0.145 workload · Tenstorrent · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.02 input / $0.50 output per 1M tokens · tenstorrent/fp4 · quantization=fp4.5Google: Gemma 4 31B · 58.4% LiveBench Design · $0.185 workload · CoreWeave · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.10 input / $0.34 output per 1M tokens · coreweave/fp4 · quantization=fp4.6Qwen: Qwen3.8 Flash · 72.8% LiveBench Design · $0.2675 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.15 input / $0.47 output per 1M tokens · alibaba/us-east-1.7DeepSeek-V4-Flash-Vision-Exp · 70.7% LiveBench Design · $0.3773 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.2156 input / $0.6468 output per 1M tokens · deepinfra/fp8 · quantization=fp8.8Reflection: Beam 1.0 501B A23B · 67.9% LiveBench Design · $0.50 workload · Nebius · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.25 input / $1.00 output per 1M tokens · nebius/fp8 · quantization=fp8.9Xiaomi: MiMo-V2.6-Pro · 78.5% LiveBench Design · $0.6475 workload · DeepInfra · via OpenRouter · Evaluation: Effort: high · single run. Price: $0.43 input / $0.87 output per 1M tokens · deepinfra/fp8 · quantization=fp8.10GLM-5.3 · 77.3% LiveBench Design · $0.8763 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.50 input / $1.505 output per 1M tokens · sail-research/us · quantization=fp8.11Step-5-Preview · 76.9% LiveBench Design · $1.675 workload · DeepInfra · Evaluation: Effort: max · single run. Price: $1.00 input / $2.70 output per 1M tokens.12OpenAI: GPT-6.1 Sol · 82.1% LiveBench Design · $2.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $1.00 input / $5.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.13Google: Gemini 4 Argon · 73.7% LiveBench Design · $2.25 workload · Google AI Studio · via OpenRouter · Evaluation: Effort: high · single run. Price: $1.00 input / $5.00 output per 1M tokens · google-ai-studio/flex · tier=flex.14Meta: Muse Spark Open · 60.3% LiveBench Design · $2.3125 workload · baseten · via Hugging Face · Evaluation: Effort: max · single run. Price: $1.25 input / $4.25 output per 1M tokens.15Kimi-K3 · 77.2% LiveBench Design · $2.529 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.504 input / $8.10 output per 1M tokens · sail-research/fp4 · quantization=fp4.16Qwen: Qwen3.8 2.4T A95B · 78.6% LiveBench Design · $3.50 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $6.00 output per 1M tokens · alibaba.17Anthropic: Claude Sonnet 5.5 · 85% LiveBench Design · $4.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $10.00 output per 1M tokens · amazon-bedrock.18Anthropic: Claude Opus 5.5 · 86.9% LiveBench Design · $9.00 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $4.00 input / $20.00 output per 1M tokens · amazon-bedrock.19OpenAI: GPT-6 Astra · 82% LiveBench Design · $11.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $5.00 input / $25.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.20Anthropic: Claude Fable 5.1 · 83.4% LiveBench Design · $22.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $10.00 input / $50.00 output per 1M tokens · amazon-bedrock.21LiveBench Design score versus workload cost40%60%80%100%$0.01$0.10$1$10$100Higher score is betterWorkload cost · USD · log scaleNVIDIA: Nemotron 3.5 Lightning · 43.9% LiveBench Design · $0.055 workload · Darkbloom · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.025 input / $0.12 output per 1M tokens · darkbloom/int4 · quantization=int4.OpenAI: GPT-6 Luna · 82.5% LiveBench Design · $0.1125 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.05 input / $0.25 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.DeepSeek: DeepSeek V4.1 Flash · 77% LiveBench Design · $0.135 workload · Decart · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.09 input / $0.18 output per 1M tokens · decart/fp4 · quantization=fp4.GLM-5.3-Flash · 77.2% LiveBench Design · $0.1375 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.075 input / $0.25 output per 1M tokens · deepinfra/fp4 · quantization=fp4.Qwen3.8-27B · 75.9% LiveBench Design · $0.145 workload · Tenstorrent · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.02 input / $0.50 output per 1M tokens · tenstorrent/fp4 · quantization=fp4.Google: Gemma 4 31B · 58.4% LiveBench Design · $0.185 workload · CoreWeave · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.10 input / $0.34 output per 1M tokens · coreweave/fp4 · quantization=fp4.Qwen: Qwen3.8 Flash · 72.8% LiveBench Design · $0.2675 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.15 input / $0.47 output per 1M tokens · alibaba/us-east-1.DeepSeek-V4-Flash-Vision-Exp · 70.7% LiveBench Design · $0.3773 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.2156 input / $0.6468 output per 1M tokens · deepinfra/fp8 · quantization=fp8.Reflection: Beam 1.0 501B A23B · 67.9% LiveBench Design · $0.50 workload · Nebius · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.25 input / $1.00 output per 1M tokens · nebius/fp8 · quantization=fp8.Xiaomi: MiMo-V2.6-Pro · 78.5% LiveBench Design · $0.6475 workload · DeepInfra · via OpenRouter · Evaluation: Effort: high · single run. Price: $0.43 input / $0.87 output per 1M tokens · deepinfra/fp8 · quantization=fp8.GLM-5.3 · 77.3% LiveBench Design · $0.8763 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.50 input / $1.505 output per 1M tokens · sail-research/us · quantization=fp8.Step-5-Preview · 76.9% LiveBench Design · $1.675 workload · DeepInfra · Evaluation: Effort: max · single run. Price: $1.00 input / $2.70 output per 1M tokens.OpenAI: GPT-6.1 Sol · 82.1% LiveBench Design · $2.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $1.00 input / $5.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.Google: Gemini 4 Argon · 73.7% LiveBench Design · $2.25 workload · Google AI Studio · via OpenRouter · Evaluation: Effort: high · single run. Price: $1.00 input / $5.00 output per 1M tokens · google-ai-studio/flex · tier=flex.Meta: Muse Spark Open · 60.3% LiveBench Design · $2.3125 workload · baseten · via Hugging Face · Evaluation: Effort: max · single run. Price: $1.25 input / $4.25 output per 1M tokens.Kimi-K3 · 77.2% LiveBench Design · $2.529 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.504 input / $8.10 output per 1M tokens · sail-research/fp4 · quantization=fp4.Qwen: Qwen3.8 2.4T A95B · 78.6% LiveBench Design · $3.50 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $6.00 output per 1M tokens · alibaba.Anthropic: Claude Sonnet 5.5 · 85% LiveBench Design · $4.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $10.00 output per 1M tokens · amazon-bedrock.Anthropic: Claude Opus 5.5 · 86.9% LiveBench Design · $9.00 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $4.00 input / $20.00 output per 1M tokens · amazon-bedrock.OpenAI: GPT-6 Astra · 82% LiveBench Design · $11.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $5.00 input / $25.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.Anthropic: Claude Fable 5.1 · 83.4% LiveBench Design · $22.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $10.00 input / $50.00 output per 1M tokens · amazon-bedrock.NVIDIA: Nemotron 3.5 Lightning · 43.9% LiveBench Design · $0.055 workload · Darkbloom · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.025 input / $0.12 output per 1M tokens · darkbloom/int4 · quantization=int4.1OpenAI: GPT-6 Luna · 82.5% LiveBench Design · $0.1125 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.05 input / $0.25 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.2DeepSeek: DeepSeek V4.1 Flash · 77% LiveBench Design · $0.135 workload · Decart · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.09 input / $0.18 output per 1M tokens · decart/fp4 · quantization=fp4.3GLM-5.3-Flash · 77.2% LiveBench Design · $0.1375 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.075 input / $0.25 output per 1M tokens · deepinfra/fp4 · quantization=fp4.4Qwen3.8-27B · 75.9% LiveBench Design · $0.145 workload · Tenstorrent · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.02 input / $0.50 output per 1M tokens · tenstorrent/fp4 · quantization=fp4.5Google: Gemma 4 31B · 58.4% LiveBench Design · $0.185 workload · CoreWeave · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.10 input / $0.34 output per 1M tokens · coreweave/fp4 · quantization=fp4.6Qwen: Qwen3.8 Flash · 72.8% LiveBench Design · $0.2675 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.15 input / $0.47 output per 1M tokens · alibaba/us-east-1.7DeepSeek-V4-Flash-Vision-Exp · 70.7% LiveBench Design · $0.3773 workload · DeepInfra · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.2156 input / $0.6468 output per 1M tokens · deepinfra/fp8 · quantization=fp8.8Reflection: Beam 1.0 501B A23B · 67.9% LiveBench Design · $0.50 workload · Nebius · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.25 input / $1.00 output per 1M tokens · nebius/fp8 · quantization=fp8.9Xiaomi: MiMo-V2.6-Pro · 78.5% LiveBench Design · $0.6475 workload · DeepInfra · via OpenRouter · Evaluation: Effort: high · single run. Price: $0.43 input / $0.87 output per 1M tokens · deepinfra/fp8 · quantization=fp8.10GLM-5.3 · 77.3% LiveBench Design · $0.8763 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.50 input / $1.505 output per 1M tokens · sail-research/us · quantization=fp8.11Step-5-Preview · 76.9% LiveBench Design · $1.675 workload · DeepInfra · Evaluation: Effort: max · single run. Price: $1.00 input / $2.70 output per 1M tokens.12OpenAI: GPT-6.1 Sol · 82.1% LiveBench Design · $2.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $1.00 input / $5.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.13Google: Gemini 4 Argon · 73.7% LiveBench Design · $2.25 workload · Google AI Studio · via OpenRouter · Evaluation: Effort: high · single run. Price: $1.00 input / $5.00 output per 1M tokens · google-ai-studio/flex · tier=flex.14Meta: Muse Spark Open · 60.3% LiveBench Design · $2.3125 workload · baseten · via Hugging Face · Evaluation: Effort: max · single run. Price: $1.25 input / $4.25 output per 1M tokens.15Kimi-K3 · 77.2% LiveBench Design · $2.529 workload · Sail Research · via OpenRouter · Evaluation: Effort: max · single run. Price: $0.504 input / $8.10 output per 1M tokens · sail-research/fp4 · quantization=fp4.16Qwen: Qwen3.8 2.4T A95B · 78.6% LiveBench Design · $3.50 workload · Alibaba · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $6.00 output per 1M tokens · alibaba.17Anthropic: Claude Sonnet 5.5 · 85% LiveBench Design · $4.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $2.00 input / $10.00 output per 1M tokens · amazon-bedrock.18Anthropic: Claude Opus 5.5 · 86.9% LiveBench Design · $9.00 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $4.00 input / $20.00 output per 1M tokens · amazon-bedrock.19OpenAI: GPT-6 Astra · 82% LiveBench Design · $11.25 workload · OpenAI · via OpenRouter · Evaluation: Effort: max · single run. Price: $5.00 input / $25.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.20Anthropic: Claude Fable 5.1 · 83.4% LiveBench Design · $22.50 workload · Amazon Bedrock · via OpenRouter · Evaluation: Effort: max · single run. Price: $10.00 input / $50.00 output per 1M tokens · amazon-bedrock.21

Numbers match the model key. Shared positions show an index range.

Model key Score / workload

  1. NVIDIA: Nemotron 3.5 Lightning43.9% / $0.055
  2. OpenAI: GPT-6 Luna82.5% / $0.1125
  3. DeepSeek: DeepSeek V4.1 Flash77% / $0.135
  4. GLM-5.3-Flash77.2% / $0.1375
  5. Qwen3.8-27B75.9% / $0.145
  6. Google: Gemma 4 31B58.4% / $0.185
  7. Qwen: Qwen3.8 Flash72.8% / $0.2675
  8. DeepSeek-V4-Flash-Vision-Exp70.7% / $0.3773
  9. Reflection: Beam 1.0 501B A23B67.9% / $0.50
  10. Xiaomi: MiMo-V2.6-Pro78.5% / $0.6475
  11. GLM-5.377.3% / $0.8763
  12. Step-5-Preview76.9% / $1.675
  13. OpenAI: GPT-6.1 Sol82.1% / $2.25
  14. Google: Gemini 4 Argon73.7% / $2.25
  15. Meta: Muse Spark Open60.3% / $2.3125
  16. Kimi-K377.2% / $2.529
  17. Qwen: Qwen3.8 2.4T A95B78.6% / $3.50
  18. Anthropic: Claude Sonnet 5.585% / $4.50
  19. Anthropic: Claude Opus 5.586.9% / $9.00
  20. OpenAI: GPT-6 Astra82% / $11.25
  21. Anthropic: Claude Fable 5.183.4% / $22.50

Pareto frontier

Frontier: no result is cheaper with an equal or better score, or equally priced with a better score. Each point uses its lowest generally available workload price from one endpoint; evaluation and provider configurations remain visible.

48 results · percent

Page 1 / 1
LiveBench Design results, configurations and model prices
#ModelLiveBench DesignConfigurationAPI rate / unitSource
1Anthropic: Claude Opus 5.5anthropic86.9%Effort: max · single runIndependent result$4.00 in / $20.00 out/ 1M tokens · Amazon Bedrock · via OpenRouteramazon-bedrockResult ↗Oct 17, 2026
2Anthropic: Claude Sonnet 5.5anthropic85%Effort: max · single runIndependent result$2.00 in / $10.00 out/ 1M tokens · Amazon Bedrock · via OpenRouteramazon-bedrockResult ↗Oct 17, 2026
3Claude Fable 5Anthropic84.7%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
4Anthropic: Claude Fable 5.1anthropic83.4%Effort: max · single runIndependent result$10.00 in / $50.00 out/ 1M tokens · Amazon Bedrock · via OpenRouteramazon-bedrockResult ↗Oct 17, 2026
5Claude Opus 5Anthropic83%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
6OpenAI: GPT-6 Lunaopenai82.5%Effort: max · single runIndependent result$0.05 in / $0.25 out/ 1M tokens · OpenAI · via OpenRouteropenai/flex · tier=flex · prompt ≤ 272000 tokensResult ↗Oct 17, 2026
7Claude Haiku 5.5Anthropic82.2%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
8GPT-6 SolOpenAI82.2%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
9OpenAI: GPT-6.1 Solopenai82.1%Effort: max · single runIndependent result$1.00 in / $5.00 out/ 1M tokens · OpenAI · via OpenRouteropenai/flex · tier=flex · prompt ≤ 272000 tokensResult ↗Oct 17, 2026
10Claude Sonnet 5Anthropic82%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
11OpenAI: GPT-6 Astraopenai82%Effort: max · single runIndependent result$5.00 in / $25.00 out/ 1M tokens · OpenAI · via OpenRouteropenai/flex · tier=flex · prompt ≤ 272000 tokensResult ↗Oct 17, 2026
12GPT-5.6 SolOpenAI81.6%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
13Grok 4.6xAI79.8%Effort: xhigh · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
14Claude Opus 4.8Anthropic78.8%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
15Qwen: Qwen3.8 2.4T A95Bqwen78.6%Effort: max · single runIndependent result$2.00 in / $6.00 out/ 1M tokens · Alibaba · via OpenRouteralibabaResult ↗Oct 17, 2026
16Xiaomi: MiMo-V2.6-Proxiaomi78.5%Effort: high · single runIndependent result$0.43 in / $0.87 out/ 1M tokens · DeepInfra · via OpenRouterdeepinfra/fp8 · quantization=fp8Result ↗Oct 17, 2026
17Grok 4.5xAI78.1%Effort: xhigh · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
18Grok 4.7xAI78%Effort: xhigh · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
19GLM-5.3zai-org77.3%Effort: max · single runIndependent result$0.0632 in / $4.40 out/ 1M tokens · Relace · via OpenRouterrelaceResult ↗Oct 17, 2026
20GLM-5.3-Flashzai-org77.2%Effort: max · single runIndependent result$0.06 in / $1.60 out/ 1M tokens · Reka · via OpenRouterrekaResult ↗Oct 17, 2026
21Kimi-K3moonshotai77.2%Effort: max · single runIndependent result$0.27 in / $14.00 out/ 1M tokens · Relace · via OpenRouterrelace/fp4 · quantization=fp4Result ↗Oct 17, 2026
22DeepSeek: DeepSeek V4.1 Flashdeepseek77%Effort: max · single runIndependent result$0.09 in / $0.18 out/ 1M tokens · Decart · via OpenRouterdecart/fp4 · quantization=fp4Result ↗Oct 17, 2026
23Step-5-Previewstepfun-ai76.9%Effort: max · single runIndependent result$1.00 in / $2.70 out/ 1M tokens · DeepInfraResult ↗Oct 17, 2026
24smaug-flashUnknown76.2%Effort not specified · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
25GPT-5.6 LunaOpenAI76%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
26GPT-5.6 TerraOpenAI76%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
27Qwen3.8-27BQwen75.9%Effort: max · single runIndependent result$0.02 in / $0.50 out/ 1M tokens · Tenstorrent · via OpenRoutertenstorrent/fp4 · quantization=fp4Result ↗Oct 17, 2026
28Muse Wonder 1.0Meta75.1%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
29Muse Spark 1.3Meta74.8%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
30Google: Gemini 4 Argongoogle73.7%Effort: high · single runIndependent result$1.00 in / $5.00 out/ 1M tokens · Google AI Studio · via OpenRoutergoogle-ai-studio/flex · tier=flexResult ↗Oct 17, 2026
31Gemini 3.7 FlashGoogle73.2%Effort: high · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
32Qwen: Qwen3.8 Flashqwen72.8%Effort: max · single runIndependent result$0.15 in / $0.47 out/ 1M tokens · Alibaba · via OpenRouteralibaba/us-east-1Result ↗Oct 17, 2026
33Gemini 3.8 FlashGoogle72.7%Effort: high · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
34Claude Sonnet 4.6Anthropic71.8%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
35DeepSeek-V4-Flash-Vision-Expdeepseek-ai70.7%Effort: max · single runIndependent result$0.2156 in / $0.6468 out/ 1M tokens · DeepInfra · via OpenRouterdeepinfra/fp8 · quantization=fp8Result ↗Oct 17, 2026
36GPT-5.5OpenAI70.3%Effort: xhigh · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
37Reflection: Beam 1.0 501B A23Breflection67.9%Effort: max · single runIndependent result$0.25 in / $1.00 out/ 1M tokens · Nebius · via OpenRouternebius/fp8 · quantization=fp8Result ↗Oct 17, 2026
38Muse Spark 1.2Meta67.1%Effort: xhigh · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
39MiniMax M3MiniMax66.2%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
40Mistral Large 4Mistral AI65.6%Effort: high · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
41Gemini 3.1 ProGoogle61.6%Effort: high · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
42Nemotron 3.5 Super VLNVIDIA60.7%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
43Meta: Muse Spark Openmeta60.3%Effort: max · single runIndependent result$1.25 in / $4.25 out/ 1M tokens · baseten · via Hugging FaceResult ↗Oct 17, 2026
44Claude Haiku 4.5Anthropic59.9%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
45Nemotron 3 UltraNVIDIA58.6%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
46Google: Gemma 4 31Bgoogle58.4%Effort: max · single runIndependent result$0.10 in / $0.34 out/ 1M tokens · CoreWeave · via OpenRoutercoreweave/fp4 · quantization=fp4Result ↗Oct 17, 2026
47InklingThinking Machines58.3%Effort: max · single runIndependent resultSee provider quotesResult ↗Oct 17, 2026
48NVIDIA: Nemotron 3.5 Lightningnvidia43.9%Effort: max · single runIndependent result$0.025 in / $0.12 out/ 1M tokens · Darkbloom · via OpenRouterdarkbloom/int4 · quantization=int4Result ↗Oct 17, 2026