Benchmark explorer.
LiveBench Agentic2.0 · 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 Agentic · 1M input + 250K output tokens · uncached USD
22 priced resultsPareto frontier
Anthropic: Claude Opus 5.5 ↗85% LiveBench Agentic · $9.00 workload · Amazon Bedrock · via OpenRouter
Evaluation: Effort: max · single run. Price: $4.00 input / $20.00 output per 1M tokens · amazon-bedrock.
Numbers match the model key. Shared positions show an index range.
Model key Score / workload
- GLM-5.3-Flash28.4% / $0.0534
- NVIDIA: Nemotron 3.5 Lightning8.3% / $0.055
- DeepSeek-V4.1-Flash-101750.9% / $0.0875
- OpenAI: GPT-6 Luna48.1% / $0.1125
- DeepSeek: DeepSeek V4.1 Flash40.1% / $0.135
- Google: Gemma 4 31B13.3% / $0.185
- Qwen: Qwen3.8 Flash37.1% / $0.2675
- Qwen3.8-27B27.9% / $0.3515
- DeepSeek-V4-Flash-Vision-Exp39% / $0.3773
- GLM-5.335.9% / $0.429
- Reflection: Beam 1.0 501B A23B17.3% / $0.50
- Xiaomi: MiMo-V2.6-Pro47.5% / $0.5828
- Step-5-Preview27.5% / $1.675
- OpenAI: GPT-6.1 Sol73% / $2.25
- Google: Gemini 4 Argon69.9% / $2.25
- Meta: Muse Spark Open18.9% / $2.3125
- Kimi-K342.8% / $2.575
- Qwen: Qwen3.8 2.4T A95B42.3% / $3.50
- Anthropic: Claude Sonnet 5.578.8% / $4.50
- Anthropic: Claude Opus 5.585% / $9.00
- OpenAI: GPT-6 Astra82.4% / $11.25
- Anthropic: Claude Fable 5.180.8% / $22.50
Pareto frontier
- GLM-5.3-FlashScore28.4%Workload cost$0.0534OpenInference · via OpenRouter · open-inference/fp4 · quantization=fp4Evaluation: Effort: max · single run. Price: $0.0107 input / $0.1707 output per 1M tokens · open-inference/fp4 · quantization=fp4.
- DeepSeek-V4.1-Flash-1017Score50.9%Workload cost$0.0875OpenInference · via OpenRouter · open-inference/fp4 · quantization=fp4Evaluation: Effort: max · single run. Price: $0.025 input / $0.25 output per 1M tokens · open-inference/fp4 · quantization=fp4.
- OpenAI: GPT-6.1 SolScore73%Workload cost$2.25OpenAI · via OpenRouter · openai/flex · tier=flex · prompt ≤ 272000 tokensEvaluation: Effort: max · single run. Price: $1.00 input / $5.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.
- Anthropic: Claude Sonnet 5.5Score78.8%Workload cost$4.50Amazon Bedrock · via OpenRouter · amazon-bedrockEvaluation: Effort: max · single run. Price: $2.00 input / $10.00 output per 1M tokens · amazon-bedrock.
- Anthropic: Claude Opus 5.5Score85%Workload cost$9.00Amazon Bedrock · via OpenRouter · amazon-bedrockEvaluation: Effort: max · single run. Price: $4.00 input / $20.00 output per 1M tokens · amazon-bedrock.
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.
| # | Model | LiveBench Agentic | Configuration | API rate / unit | Source |
|---|---|---|---|---|---|
| 1 | Anthropic: Claude Opus 5.5anthropic | 85% | Effort: max · single runIndependent result | $4.00 in / $20.00 out/ 1M tokens · Amazon Bedrock · via OpenRouteramazon-bedrock | Result ↗Oct 18, 2026 |
| 2 | OpenAI: GPT-6 Astraopenai | 82.4% | Effort: max · single runIndependent result | $5.00 in / $25.00 out/ 1M tokens · OpenAI · via OpenRouteropenai/flex · tier=flex · prompt ≤ 272000 tokens | Result ↗Oct 18, 2026 |
| 3 | Anthropic: Claude Fable 5.1anthropic | 80.8% | Effort: max · single runIndependent result | $10.00 in / $50.00 out/ 1M tokens · Amazon Bedrock · via OpenRouteramazon-bedrock | Result ↗Oct 18, 2026 |
| 4 | Anthropic: Claude Sonnet 5.5anthropic | 78.8% | Effort: max · single runIndependent result | $2.00 in / $10.00 out/ 1M tokens · Amazon Bedrock · via OpenRouteramazon-bedrock | Result ↗Oct 18, 2026 |
| 5 | OpenAI: GPT-6.1 Solopenai | 73% | Effort: max · single runIndependent result | $1.00 in / $5.00 out/ 1M tokens · OpenAI · via OpenRouteropenai/flex · tier=flex · prompt ≤ 272000 tokens | Result ↗Oct 18, 2026 |
| 6 | Google: Gemini 4 Argongoogle | 69.9% | Effort: high · single runIndependent result | $1.00 in / $5.00 out/ 1M tokens · Google AI Studio · via OpenRoutergoogle-ai-studio/flex · tier=flex | Result ↗Oct 18, 2026 |
| 7 | GPT-6 SolOpenAI | 66.9% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 8 | Claude Opus 5Anthropic | 62.1% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 9 | Claude Haiku 5.5Anthropic | 56.6% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 10 | Claude Fable 5Anthropic | 53.2% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 11 | Muse Wonder 1.0Meta | 53.2% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 12 | DeepSeek-V4.1-Flash-1017deepseek-ai | 50.9% | Effort: max · single runIndependent result | $0.025 in / $0.25 out/ 1M tokens · OpenInference · via OpenRouteropen-inference/fp4 · quantization=fp4 | Result ↗Oct 18, 2026 |
| 13 | Grok 4.7xAI | 50.1% | Effort: xhigh · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 14 | GPT-5.6 SolOpenAI | 48.5% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 15 | GPT-5.6 TerraOpenAI | 48.4% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 16 | Claude Opus 4.8Anthropic | 48.3% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 17 | OpenAI: GPT-6 Lunaopenai | 48.1% | Effort: max · single runIndependent result | $0.05 in / $0.25 out/ 1M tokens · OpenAI · via OpenRouteropenai/flex · tier=flex · prompt ≤ 272000 tokens | Result ↗Oct 18, 2026 |
| 18 | Xiaomi: MiMo-V2.6-Proxiaomi | 47.5% | Effort: high · single runIndependent result | $0.387 in / $0.783 out/ 1M tokens · DeepInfra · via OpenRouterdeepinfra/fp8 · quantization=fp8 | Result ↗Oct 18, 2026 |
| 19 | GPT-5.5OpenAI | 44.6% | Effort: xhigh · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 20 | Kimi-K3moonshotai | 42.8% | Effort: max · single runIndependent result | $0.238 in / $16.00 out/ 1M tokens · Wafer · via OpenRouterwafer · quantization=mxfp4 | Result ↗Oct 18, 2026 |
| 21 | Qwen: Qwen3.8 2.4T A95Bqwen | 42.3% | Effort: max · single runIndependent result | $2.00 in / $6.00 out/ 1M tokens · Alibaba · via OpenRouteralibaba | Result ↗Oct 18, 2026 |
| 22 | Grok 4.6xAI | 40.7% | Effort: xhigh · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 23 | Muse Spark 1.3Meta | 40.4% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 24 | DeepSeek: DeepSeek V4.1 Flashdeepseek | 40.1% | Effort: max · single runIndependent result | $0.07 in / $0.50 out/ 1M tokens · OpenInference · via OpenRouteropen-inference/fp4 · quantization=fp4 | Result ↗Oct 18, 2026 |
| 25 | Claude Sonnet 5Anthropic | 39% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 26 | DeepSeek-V4-Flash-Vision-Expdeepseek-ai | 39% | Effort: max · single runIndependent result | $0.2156 in / $0.6468 out/ 1M tokens · DeepInfra · via OpenRouterdeepinfra/fp8 · quantization=fp8 | Result ↗Oct 18, 2026 |
| 27 | Qwen: Qwen3.8 Flashqwen | 37.1% | Effort: max · single runIndependent result | $0.15 in / $0.47 out/ 1M tokens · Alibaba · via OpenRouteralibaba/us-east-1 | Result ↗Oct 18, 2026 |
| 28 | GLM-5.3zai-org | 35.9% | Effort: max · single runIndependent result | $0.079 in / $1.40 out/ 1M tokens · Wafer · via OpenRouterwafer/us · quantization=fp4 | Result ↗Oct 18, 2026 |
| 29 | GPT-5.6 LunaOpenAI | 30.4% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 30 | Gemini 3.8 FlashGoogle | 30.1% | Effort: high · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 31 | GLM-5.3-Flashzai-org | 28.4% | Effort: max · single runIndependent result | $0.0107 in / $0.1707 out/ 1M tokens · OpenInference · via OpenRouteropen-inference/fp4 · quantization=fp4 | Result ↗Oct 18, 2026 |
| 32 | Gemini 3.7 FlashGoogle | 28.3% | Effort: high · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 33 | Grok 4.5xAI | 27.9% | Effort: xhigh · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 34 | Qwen3.8-27BQwen | 27.9% | Effort: max · single runIndependent result | $0.035 in / $2.20 out/ 1M tokens · Darkbloom · via OpenRouterdarkbloom/fp4 · quantization=fp4 | Result ↗Oct 18, 2026 |
| 35 | Step-5-Previewstepfun-ai | 27.5% | Effort: max · single runIndependent result | $1.00 in / $2.70 out/ 1M tokens · DeepInfra | Result ↗Oct 18, 2026 |
| 36 | smaug-flashUnknown | 27.1% | Effort not specified · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 37 | Gemini 3.1 ProGoogle | 23.9% | Effort: high · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 38 | Claude Sonnet 4.6Anthropic | 23.1% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 39 | Muse Spark 1.2Meta | 21.3% | Effort: xhigh · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 40 | Meta: Muse Spark Openmeta | 18.9% | Effort: max · single runIndependent result | $1.25 in / $4.25 out/ 1M tokens · baseten · via Hugging Face | Result ↗Oct 18, 2026 |
| 41 | Reflection: Beam 1.0 501B A23Breflection | 17.3% | Effort: max · single runIndependent result | $0.25 in / $1.00 out/ 1M tokens · Nebius · via OpenRouternebius/fp8 · quantization=fp8 | Result ↗Oct 18, 2026 |
| 42 | Nemotron 3.5 Super VLNVIDIA | 15.8% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 43 | InklingThinking Machines | 14.1% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 44 | Google: Gemma 4 31Bgoogle | 13.3% | Effort: max · single runIndependent result | $0.10 in / $0.34 out/ 1M tokens · CoreWeave · via OpenRoutercoreweave/fp4 · quantization=fp4 | Result ↗Oct 18, 2026 |
| 45 | MiniMax M3MiniMax | 12.4% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 46 | Mistral Large 4Mistral AI | 11.8% | Effort: high · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 47 | Nemotron 3 UltraNVIDIA | 11.2% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 48 | Claude Haiku 4.5Anthropic | 11.1% | Effort: max · single runIndependent result | See provider quotes | Result ↗Oct 18, 2026 |
| 49 | NVIDIA: Nemotron 3.5 Lightningnvidia | 8.3% | Effort: max · single runIndependent result | $0.025 in / $0.12 out/ 1M tokens · Darkbloom · via OpenRouterdarkbloom/int4 · quantization=int4 | Result ↗Oct 18, 2026 |