Benchmark explorer.
CritPtAA · Under reviewAA Index 4.3.2 collection · Higher is better
Source ↗Method
Artificial Analysis evaluation; source marks this result under review. Index 4.3.2 collection.
Score × cost
Provisional score × price
CritPt · AA · Under review · 1M input + 250K output tokens · uncached USD
17 priced resultsProvisional frontier
OpenAI: GPT-6.1 Sol ↗31.71% CritPt · AA · Under review · $2.25 workload · OpenAI · via OpenRouter
Evaluation: Effort: max · Max. Price: $1.00 input / $5.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.
Numbers match the model key. Shared positions show an index range.
Model key Score / workload
- DeepSeek-V4.1-Flash-101724% / $0.075
- GLM-5.3-Flash15.43% / $0.088
- Qwen3.8-27B5.43% / $0.145
- OpenAI: GPT-6 Luna19.43% / $0.225
- GLM-5.319.14% / $0.429
- Reflection: Beam 1.0 501B A23B13.14% / $0.50
- Xiaomi: MiMo-V2.6-Pro26.57% / $0.5828
- Kimi-K323.43% / $1.55
- Step-5-Preview20.86% / $1.675
- Thinking Machines: Inkling5.43% / $1.9625
- OpenAI: GPT-6.1 Sol31.71% / $2.25
- Google: Gemini 4 Argon27.14% / $2.25
- Meta: Muse Spark Open14.86% / $2.3125
- Anthropic: Claude Sonnet 5.531.43% / $4.50
- Anthropic: Claude Opus 5.531.71% / $9.00
- OpenAI: GPT-6 Astra31.71% / $11.25
- Anthropic: Claude Fable 5.129.71% / $22.50
Provisional frontier
- DeepSeek-V4.1-Flash-1017AA · Under reviewScore24%Workload cost$0.075Relace · via OpenRouter · relaceEvaluation: Effort: max · Max. Price: $0.05 input / $0.10 output per 1M tokens · relace.
- Xiaomi: MiMo-V2.6-ProAA · Under reviewScore26.57%Workload cost$0.5828DeepInfra · via OpenRouter · deepinfra/fp8 · quantization=fp8Evaluation: Effort not specified. Price: $0.387 input / $0.783 output per 1M tokens · deepinfra/fp8 · quantization=fp8.
- OpenAI: GPT-6.1 SolAA · Under reviewScore31.71%Workload cost$2.25OpenAI · via OpenRouter · openai/flex · tier=flex · prompt ≤ 272000 tokensEvaluation: Effort: max · Max. Price: $1.00 input / $5.00 output per 1M tokens · openai/flex · tier=flex · prompt ≤ 272000 tokens.
Provisional 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 | CritPt | Configuration | API rate / unit | Source |
|---|---|---|---|---|---|
| 1 | Muse Wonder FullMeta | 32.86%AA · Under review | Effort: max · MaxIndependent result | See provider quotes | Result ↗Oct 20, 2026 |
| 2 | Anthropic: Claude Opus 5.5anthropic | 31.71%AA · Under review | Effort: max · Max, Default FallbackIndependent result | $4.00 in / $20.00 out/ 1M tokens · Amazon Bedrock · via OpenRouteramazon-bedrock | Result ↗Oct 20, 2026 |
| 3 | OpenAI: GPT-6 Astraopenai | 31.71%AA · Under review | Effort: max · MaxIndependent result | $5.00 in / $25.00 out/ 1M tokens · OpenAI · via OpenRouteropenai/flex · tier=flex · prompt ≤ 272000 tokens | Result ↗Oct 20, 2026 |
| 4 | OpenAI: GPT-6.1 Solopenai | 31.71%AA · Under review | Effort: max · MaxIndependent result | $1.00 in / $5.00 out/ 1M tokens · OpenAI · via OpenRouteropenai/flex · tier=flex · prompt ≤ 272000 tokens | Result ↗Oct 20, 2026 |
| 5 | Anthropic: Claude Sonnet 5.5anthropic | 31.43%AA · Under review | Effort: max · Max, Default FallbackIndependent result | $2.00 in / $10.00 out/ 1M tokens · Amazon Bedrock · via OpenRouteramazon-bedrock | Result ↗Oct 20, 2026 |
| 6 | Anthropic: Claude Fable 5.1anthropic | 29.71%AA · Under review | Effort: max · Max, Default FallbackIndependent result | $10.00 in / $50.00 out/ 1M tokens · Amazon Bedrock · via OpenRouteramazon-bedrock | Result ↗Oct 20, 2026 |
| 7 | Muse WonderMeta | 28.29%AA · Under review | Effort: max · MaxIndependent result | See provider quotes | Result ↗Oct 20, 2026 |
| 8 | Google: Gemini 4 Argongoogle | 27.14%AA · Under review | Effort: high · HighIndependent result | $1.00 in / $5.00 out/ 1M tokens · Google AI Studio · via OpenRoutergoogle-ai-studio/flex · tier=flex | Result ↗Oct 20, 2026 |
| 9 | Xiaomi: MiMo-V2.6-Proxiaomi | 26.57%AA · Under review | Effort not specifiedIndependent result | $0.387 in / $0.783 out/ 1M tokens · DeepInfra · via OpenRouterdeepinfra/fp8 · quantization=fp8 | Result ↗Oct 20, 2026 |
| 10 | DeepSeek-V4.1-Flash-1017deepseek-ai | 24%AA · Under review | Effort: max · MaxIndependent result | $0.04 in / $0.60 out/ 1M tokens · Morph · via OpenRoutermorph/fp8 · quantization=fp8 | Result ↗Oct 20, 2026 |
| 11 | Kimi-K3moonshotai | 23.43%AA · Under review | Effort: max · MaxIndependent result | $0.238 in / $16.00 out/ 1M tokens · Wafer · via OpenRouterwafer · quantization=mxfp4 | Result ↗Oct 20, 2026 |
| 12 | MiniMax-M3.1-FlashMiniMax | 22.29%AA · Under review | Effort not specifiedIndependent result | See provider quotes | Result ↗Oct 20, 2026 |
| 13 | Step-5-Previewstepfun-ai | 20.86%AA · Under review | Effort not specifiedIndependent result | $1.00 in / $2.70 out/ 1M tokens · DeepInfra | Result ↗Oct 20, 2026 |
| 14 | OpenAI: GPT-6 Lunaopenai | 19.43%AA · Under review | Effort: max · MaxIndependent result | $0.10 in / $0.50 out/ 1M tokens · Azure · via OpenRouterazure · prompt ≤ 272000 tokens | Result ↗Oct 20, 2026 |
| 15 | GLM-5.3zai-org | 19.14%AA · Under review | Effort: max · MaxIndependent result | $0.079 in / $1.40 out/ 1M tokens · Wafer · via OpenRouterwafer/us · quantization=fp4 | Result ↗Oct 20, 2026 |
| 16 | Claude Haiku 5.5Anthropic | 18.86%AA · Under review | Effort: max · MaxIndependent result | See provider quotes | Result ↗Oct 20, 2026 |
| 17 | Gemini 3.8 FlashGoogle | 18.29%AA · Under review | Effort: high · HighIndependent result | See provider quotes | Result ↗Oct 20, 2026 |
| 18 | Grok 4.7SpaceXAI | 17.71%AA · Under review | Effort: xhigh · XhighIndependent result | See provider quotes | Result ↗Oct 20, 2026 |
| 19 | Qwen3.8 Max (0902)Alibaba | 17.71%AA · Under review | Effort not specifiedIndependent result | See provider quotes | Result ↗Oct 20, 2026 |
| 20 | GLM-5.3-Flashzai-org | 15.43%AA · Under review | Effort: maxIndependent result | $0.048 in / $0.16 out/ 1M tokens · OpenInference · via OpenRouteropen-inference/fp4 · quantization=fp4 | Result ↗Oct 20, 2026 |
| 21 | Meta: Muse Spark Openmeta | 14.86%AA · Under review | Effort: xhigh · XhighIndependent result | $1.25 in / $4.25 out/ 1M tokens · baseten · via Hugging Face | Result ↗Oct 20, 2026 |
| 22 | Reflection: Beam 1.0 501B A23Breflection | 13.14%AA · Under review | Effort not specifiedIndependent result | $0.25 in / $1.00 out/ 1M tokens · Nebius · via OpenRouternebius/fp8 · quantization=fp8 | Result ↗Oct 20, 2026 |
| 23 | Mistral Large 4 PreviewMistral | 10.57%AA · Under review | Effort not specifiedIndependent result | See provider quotes | Result ↗Oct 20, 2026 |
| 24 | Nemotron 3.5 Super VLNVIDIA | 10.57%AA · Under review | Effort not specifiedIndependent result | See provider quotes | Result ↗Oct 20, 2026 |
| 25 | Thinking Machines: Inklingthinkingmachines | 5.43%AA · Under review | Effort: xhigh · XhighIndependent result | $0.95 in / $4.05 out/ 1M tokens · deepinfra · via Hugging Face | Result ↗Oct 20, 2026 |
| 26 | Qwen3.8-27BQwen | 5.43%AA · Under review | Effort: xhigh · XhighIndependent result | $0.02 in / $0.50 out/ 1M tokens · Tenstorrent · via OpenRoutertenstorrent/fp4 · quantization=fp4 | Result ↗Oct 20, 2026 |
| 27 | K2 Horizon 375B A23BInstitute of Foundation Models | 4.57%AA · Under review | Effort not specifiedIndependent result | See provider quotes | Result ↗Oct 20, 2026 |