Note: Overall leaderboard rankings may not reflect true model quality — individual benchmarks give a clearer picture. ARC-Challenge MMLU GPQA GSM8K Artificial Analysis Intelligence Index v4.1
← Back to leaderboard

SciCode

46 models

SciCode measures an AI's ability to generate executable scientific code that solves real research problems — including data analysis, simulations, and modeling — based on natural language descriptions from scientific papers, testing both coding proficiency and domain-specific scientific understanding.

Top 5 Models Performance

Anthropic: claude-sonnet-5.5 ######################################## 61
sakana: fugu ####################################### 60.1
Anthropic: Claude Fable 5 ####################################### 60
Moonshot AI: kimi-k3 ####################################### 59
Google: Gemini 3.1 Pro Preview ####################################### 59
– 970 – 1.1T
– 2019 – 2026
Rank Model Score
🇺🇸 1 Anthropic: claude-sonnet-5.5 61
🇯🇵 2 sakana: fugu 60.1
🇺🇸 3 Anthropic: Claude Fable 5 60
🇨🇳 4 Moonshot AI: kimi-k3月之暗面 59
🇺🇸 5 Google: Gemini 3.1 Pro Preview 59
🇯🇵 6 sakana: fugu-ultra 58.7
🇺🇸 7 Meta: muse-spark-open-816b-a42b 58.5
🇺🇸 8 OpenAI: gpt-6.1-sol 54
🇺🇸 9 OpenAI: gpt-6-astra 54
❓ 10 Ornith: ornith-1.5-122b 53.8
🇺🇸 11 Anthropic: Claude Opus 4.8 53
❓ 12 nanbeige: nanbeige4.3-33b 52.6
🇨🇳 13 Moonshot AI: Kimi K2.6月之暗面 52.2
🇨🇳 14 Qwen: qwen3.8-2.4t-a95b通义千问 52
🇺🇸 15 Meta: Muse Spark 52
🇨🇳 16 Xiaomi: MiMo-V2.5 Pro小米集团 50
🇺🇸 17 NVIDIA Corporation: nvidia-nemotron-3.5-super-vl-120b-a12b 47.13
🇺🇸 18 SpaceXAI: Grok 4.3 47
🇨🇳 19 DeepSeek: DeepSeek V4 Flash深度求索 45
🇺🇸 20 SpaceXAI: Grok 4.20 45
🇺🇸 21 Meta: muse-glimmer-30b 43.6
🇨🇳 22 Xiaomi: MiMo-V2.5小米集团 43
🇨🇳 23 Xiaomi: mimo-v2-pro小米集团 42
🇺🇸 24 NVIDIA Corporation: nvidia-nemotron-3.5-bolt-74b-a9b-24gb 41.02
🇺🇸 25 SpaceXAI: Grok 3 Mini 41
🇺🇸 26 OpenAI: o3-mini 40
❓ 27 recursiveai: ripple-65b-preview 39.4
❓ 28 ifm: k2-horizon-mova-36b-a4b 38.9
❓ 29 krafton: raon-1-mini-preview 38.7
🇨🇦 30 Cohere Labs: north-mini-code-1.0 38.2
🇺🇸 31 Inception: Mercury 2 38
🇺🇸 32 SpaceXAI: Grok 3 37
❓ 33 xhtoken: spark-x2.6-4b 36.8
❓ 34 xhtoken: spark-x2.5-4b 34.7
🇺🇸 35 NVIDIA Corporation: nvidia-nemotron-3-nano-30b-a3b 33.3
❓ 36 LLM360: k2-think-v2 33
🇺🇸 37 LiquidAI: lfm-2.5-24b-a2b 32.71
🇺🇸 38 NVIDIA Corporation: nvidia-nemotron-3.5-lightning-30b-a3b-bf16 32.6
🇺🇸 39 LiquidAI: lfm-3-1.7b 28.47
🇨🇳 40 OpenBMB: minicpm5-2b 26.3
🇺🇸 41 Meta Llama: Llama 3.3 70B Instruct 26
🇨🇳 42 inclusionAI: ling-3.0-tiny 24.2
❓ 43 xhtoken: spark-x2.5-1.7b 18.2
🇺🇸 44 Google: Gemini 1.0 Pro 12
🇨🇦 45 Cohere Labs: Tiny Aya Global 4
🇦🇪 46 Technology Innovation Institute: falcon-h1r-7b 3.9