TestsBenchmarks · Coding
SciCode
Share of scientific-computing coding subproblems solved correctly (as run by Artificial Analysis).
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | 66.9% | MaxClaude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 2 | Claude Fable 5.1 | Anthropic | 63.1% | MaxClaude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 3 | Gemini 4 Argon | Google (Gemini / DeepMind) | 61.8% | HighGemini 4 Argon (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 4 | Claude Sonnet 5.5 | Anthropic | 61.0% | MaxClaude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 5 | Claude Fable 5 | Anthropic | 61.0% | MaxClaude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 6 | MiMo-V2.6-Pro | Xiaomi MiMo | 60.9% | DefaultMiMo-V2.6-Pro | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 7 | Gemini 3.7 Flash | Google (Gemini / DeepMind) | 59.8% | MediumGemini 3.7 Flash (Medium) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 8 | Muse Spark 1.3 | Meta (Meta Superintelligence Labs, Muse) | 59.7% | Extra highMuse Spark 1.3 (Xhigh) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 9 | Kimi K3 | Moonshot AI (Kimi) | 59.5% | MaxKimi K3 (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 10 | GLM-5.3 | Z.ai (Zhipu) | 59.0% | MaxGLM-5.3 (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 11 | Gemini 3.1 Pro (Preview) | Google (Gemini / DeepMind) | 59.0% | HighThinking (High) | Maker's own figureVendor-reportedGoogle ↗ | — | 19 Feb 2026 |
| 12 | Step 5 Preview | StepFun | 58.9% | DefaultStep 5 Preview | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 13 | Muse Spark 1.1 | Meta (Meta Superintelligence Labs, Muse) | 58.8% | Extra highMuse Spark 1.1 (Xhigh) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 14 | Grok 4.7 | SpaceXAI (formerly xAI) | 57.8% | HighGrok 4.7 (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 15 | GPT-5.6 Sol | OpenAI | 57.8% | HighGPT-5.6 Sol (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 16 | GPT-6 Sol | OpenAI | 57.6% | MaxGPT-6 Sol (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 17 | Muse Spark 1.2 | Meta (Meta Superintelligence Labs, Muse) | 57.4% | Extra highMuse Spark 1.2 (Xhigh) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 18 | Gemini 3.8 Flash | Google (Gemini / DeepMind) | 56.6% | HighGemini 3.8 Flash (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 19 | GPT-6 Astra | OpenAI | 56.5% | MaxGPT-6 Astra (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 20 | Grok 4.6 | SpaceXAI (formerly xAI) | 56.5% | HighGrok 4.6 (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 21 | Claude Opus 5 | Anthropic | 56.4% | MaxClaude Opus 5 (Adaptive Reasoning, Max Effort) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 22 | GPT-5.5 | OpenAI | 56.1% | HighGPT-5.5 (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 23 | GPT-6.1 Sol | OpenAI | 55.8% | HighGPT-6.1 Sol (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 24 | Grok 4.5 | SpaceXAI (formerly xAI) | 55.0% | HighGrok 4.5 (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 25 | GPT-5.6 Terra | OpenAI | 55.0% | MaxGPT-5.6 Terra (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 26 | GPT-6 Luna | OpenAI | 54.6% | MaxGPT-6 Luna (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 27 | Claude Opus 4.8 | Anthropic | 54.4% | MaxClaude Opus 4.8 (Adaptive Reasoning, Max Effort) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 28 | Claude Sonnet 5 | Anthropic | 54.3% | MaxClaude Sonnet 5 (Adaptive Reasoning, Max Effort) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 29 | Qwen3.8 2.4T A95B (open weights) | Qwen (Alibaba) | 54.1% | DefaultQwen3.8 2.4T A95B | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 30 | GPT-5.6 Luna | OpenAI | 53.6% | MaxGPT-5.6 Luna (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 31 | Qwen3.7 Max | Qwen (Alibaba) | 53.5% | Defaultthinking (vendor recommends 'Reasoning effort is set to xhigh' system prompt for reasoning tasks) | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | — | 16 May 2026 |
| 32 | Gemini 3.6 Flash | Google (Gemini / DeepMind) | 53.4% | HighGemini 3.6 Flash (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 33 | Kimi K2.6 | Moonshot AI (Kimi) | 52.2% | Defaultthinking | Maker's own figureVendor-reportedMoonshot AI ↗ | — | 20 Apr 2026 |
| 34 | Qwen3.8 Max (0902) | Qwen (Alibaba) | 52.1% | DefaultQwen3.8 Max (0902) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 35 | DeepSeek V4.1 Flash | DeepSeek | 51.9% | MaxDeepSeek V4.1 Flash (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 36 | GLM-5.3-Flash | Z.ai (Zhipu) | 51.6% | DefaultGLM 5.3 Flash | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 37 | MiMo-V2.6-Flash | Xiaomi MiMo | 51.3% | DefaultMiMo-V2.6-Flash | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 38 | Qwen3.7 Plus | Qwen (Alibaba) | 51.3% | Defaultthinking | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | — | 21 May 2026 |
| 39 | GLM-5.2 | Z.ai (Zhipu) | 51.2% | MaxGLM-5.2 (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 40 | DeepSeek V4 Pro (0813) | DeepSeek | 51.0% | MaxDeepSeek V4 Pro 0813 (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 41 | Qwen3.8-Flash-Next | Qwen (Alibaba) | 50.6% | DefaultQwen3.8-Flash-Next | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 42 | DeepSeek V4 Flash (0731) | DeepSeek | 50.3% | MaxDeepSeek V4 Flash 0731 (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 43 | DeepSeek V4 Flash Vision Exp | DeepSeek | 49.7% | MaxDeepSeek V4 Flash Vision (Max) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 44 | Hy3 | Tencent Hunyuan | 48.6% | DefaultHy3 | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 45 | MiniMax M3 | MiniMax | 47.1% | DefaultMiniMax-M3 | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 46 | Qwen3.8 27B | Qwen (Alibaba) | 46.6% | Extra highQwen3.8 27B (Xhigh) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 47 | Gemma 4 31B IT | Google (Gemini / DeepMind) | 45.5% | DefaultGemma 4 31B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 48 | Muse Glimmer 30B | Meta (Meta Superintelligence Labs, Muse) | 44.9% | HighMuse Glimmer (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 49 | Nemotron 3 Ultra | NVIDIA | 40.3% | DefaultNemotron 3 Ultra 550B A55B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 50 | Mistral Medium 3.5 | Mistral AI | 40.2% | DefaultMistral Medium 3.5 | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 51 | gpt-oss-20b | OpenAI | 38.9% | Highgpt-oss-20b (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 52 | Mistral Small 4 | Mistral AI | 38.8% | HighMistral Small 4 (Reasoning) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 53 | Command A+ | Cohere | 38.5% | DefaultCommand A+ | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 54 | Qwen3.6 35B A3B | Qwen (Alibaba) | 36.6% | DefaultQwen3.6 35B A3B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 55 | Nemotron 3 Super 120B A12B | NVIDIA | 36.2% | DefaultNemotron 3 Super 120B A12B (Reasoning) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 56 | gpt-oss-120b | OpenAI | 34.0% | Highgpt-oss-120b (High) | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 57 | Nemotron 3.5 Lightning 30B-A3B | NVIDIA | 32.1% | DefaultNemotron 3.5 Lightning | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 58 | Granite 4.2 8B | IBM Granite | 31.5% | DefaultGranite 4.2 8B | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |
| 59 | Ministral 3 14B | Mistral AI | 23.8% | DefaultMinistral 3 14B | Independent testIndependentArtificial Analysis ↗ | — | 1 Oct 2026 |