SciCode benchmark
145 AI models ranked on SciCode. Each row shows the model’s score next to its cheapest API price per 1M tokens where it has one, so you can weigh quality against cost.
Top model today
Claude Opus 5.5 (Anthropic) leads at 67%, from $4.00 per 1M input via Anthropic.
Data via arXiv:2407.13168 →Models ranked
145
on this benchmark
Top score
67%
current leader
Type
Single eval
benchmark
Updated
Oct 14, 2026
benchmark scores
Cost vs SciCode
111 priced models = reasoning model (extended thinking)
Each labelled name links to that model’s page. Curated to the cost-efficiency frontier, top scorers and cheapest so labels stay readable; the full field is in the leaderboard table below (and via “select all”). Reasoning models (extended “thinking” before answering) carry a ring around the dot.
Models ranked on SciCode
highest score first · 145 modelsMaker
| # | ||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 |  Anthropic | 67% | $4.00 via Anthropic | $20.00 via Databricks | |||||||||||||||||||||||||||||
| 2 | Claude Fable 5.1 | Anthropic | 63% | $10.00 via Anthropic | $50.00 via Anthropic | |||||||||||||||||||||||||||||
| 3 | Muse Wonder Full (Max) |  Meta | 63% | n/a | n/a | |||||||||||||||||||||||||||||
| 4 | Gemini 4 Argon |  Google | 62% | $2.00 via Google | $10.00 via Google | |||||||||||||||||||||||||||||
| 5 | Claude Fable 5 | Anthropic | 61% | $10.00 via Anthropic | $50.00 via Anthropic | |||||||||||||||||||||||||||||
| 6 | Claude Sonnet 5.5 | Anthropic | 61% | $2.00 via Anthropic | $10.00 via Anthropic | |||||||||||||||||||||||||||||
| 7 | MiMo-V2.6-Pro |  Xiaomi | 61% | $0.435 via Xiaomi Mimo | $0.87 via Xiaomi Mimo | |||||||||||||||||||||||||||||
| 8 | Muse Wonder | Other | 60% | $4.00 Routed quote | $20.00 Routed quote | |||||||||||||||||||||||||||||
| 9 | Kimi K3 |  Moonshot | 59% | $0.70 Routed quote | $12.50 via Sail | |||||||||||||||||||||||||||||
| 10 | GLM 5.3 |  Zhipu | 59% | $0.079 Routed quote | $3.08 via Sail | |||||||||||||||||||||||||||||
| 11 | Step 5 Preview | Stepfun | 59% | n/a | n/a | |||||||||||||||||||||||||||||
| 12 | Muse Spark 1.3 | Other | 59% | $1.25 via Azure | $4.25 via Azure | |||||||||||||||||||||||||||||
| 13 | Muse Spark 1.1 | Other | 59% | $1.25 via Meta | $4.25 via Meta | |||||||||||||||||||||||||||||
| 14 | Gemini 3.1 Pro Preview | Google | 59% | $2.00 via Google | $12.00 via Google | |||||||||||||||||||||||||||||
| 15 | GPT-5.6 Sol |  OpenAI | 58%high | $2.00 Routed quote | $10.00 Routed quote | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 16 | GPT-6 Sol | OpenAI | 58% | $2.00 via OpenAI | $10.00 via OpenAI | |||||||||||||||||||||||||||||
| 17 | Grok 4.7 |  xAI | 57% | $2.00 via xAI | $6.00 via xAI | |||||||||||||||||||||||||||||
| 18 | Muse Spark 1.2 | Other | 57% | $1.25 via Meta | $4.25 via Meta | |||||||||||||||||||||||||||||
| 19 | Gemini 3.7 Flash | Google | 57% | $0.75 via Google | $3.75 via Google | |||||||||||||||||||||||||||||
| 20 | Gemini 3.8 Flash | Google | 57% | $0.75 via Google | $3.75 via Google | |||||||||||||||||||||||||||||
| 21 | Grok 4.6 | xAI | 56% | $2.00 via xAI | $6.00 via xAI | |||||||||||||||||||||||||||||
| 22 | GPT-6 Astra | OpenAI | 56% | $10.00 via OpenAI | $50.00 via OpenAI | |||||||||||||||||||||||||||||
| 23 | Claude Opus 5 | Anthropic | 56% | $5.00 via Anthropic | $25.00 via Anthropic | |||||||||||||||||||||||||||||
| 24 | GPT-5.5 | OpenAI | 56%high | $5.00 via OpenAI | $30.00 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 25 | Claude Haiku 5.5 | Anthropic | 55% | $0.10 via Anthropic | $0.50 via Anthropic | |||||||||||||||||||||||||||||
| 26 | GPT-5.6 Terra | OpenAI | 55% | $2.00 via OpenAI | $12.00 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 27 | Grok 4.5 | xAI | 55% | $2.00 via xAI | $6.00 via xAI | |||||||||||||||||||||||||||||
| 28 | GPT-6 Luna | OpenAI | 55% | $0.10 via OpenAI | $0.50 via OpenAI | |||||||||||||||||||||||||||||
| 29 | Claude Opus 4.8 | Anthropic | 54% | $5.00 via Anthropic | $25.00 via Anthropic | |||||||||||||||||||||||||||||
| 30 | Claude Sonnet 5 | Anthropic | 54% | $2.00 via Anthropic | $10.00 via Anthropic | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 31 | GPT-6.1 Sol | OpenAI | 54% | $2.00 via OpenAI | $10.00 via OpenAI | |||||||||||||||||||||||||||||
| 32 | Mistral Large 4 |  Mistral | 54% | $0.68 via Mistral | $2.09 via Mistral | |||||||||||||||||||||||||||||
| 33 | Qwen3.8 2.4T A95B |  Alibaba | 54% | $2.00 via Aihubmix | $6.00 via Aihubmix | |||||||||||||||||||||||||||||
| 34 | Ling 3.1 Flash | InclusionAI | 54% | n/a | n/a | |||||||||||||||||||||||||||||
| 35 | Gemini 3.5 Flash | Google | 54% | $1.50 via Google | $9.00 via Google | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 36 | GPT-5.6 Luna | OpenAI | 54% | $0.20 via OpenAI | $1.20 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 37 | Gemini 3.6 Flash | Google | 53% | $0.75 via Google | $3.75 via Google | |||||||||||||||||||||||||||||
| 38 | Qwen3.8 Max | Alibaba | 53% | $1.65 via DeepInfra | $4.95 via DeepInfra | |||||||||||||||||||||||||||||
| 39 | GPT-5.5 Instant (June 2026) | OpenAI | 53% | n/a | n/a | |||||||||||||||||||||||||||||
| 40 | GPT-5.4 Mini | OpenAI | 52% | $0.75 via Databricks | $4.50 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 41 | Qwen3.8 Max (0902) | Alibaba | 52% | $2.00 Routed quote | $6.00 Routed quote | |||||||||||||||||||||||||||||
| 42 | JT-4.1 Flash 236B A21B | China-mobile | 52% | n/a | n/a | |||||||||||||||||||||||||||||
| 43 | JT-4.1 Flash 236B A21B | China-mobile | 52% | n/a | n/a | |||||||||||||||||||||||||||||
| 44 | DeepSeek V4.1 Flash |  DeepSeek | 52% | $0.01 via Coralbricks | $0.60 via Sail | |||||||||||||||||||||||||||||
| 45 | GLM 5.3 Flash | Zhipu | 52% | $0.11 via Sail | $0.35 via Sail | |||||||||||||||||||||||||||||
| 46 | Kimi K2.6 | Moonshot | 52% | $0.65 via Wandb | $3.40 via Novita | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 47 | MiMo-V2.6-Flash | Xiaomi | 51% | $0.14 via Xiaomi Mimo | $0.28 via Xiaomi Mimo | |||||||||||||||||||||||||||||
| 48 | GLM 5.2 | Zhipu | 51% | $0.05 Routed quote | $1.98 via Scx AI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 49 | DeepSeek V4 Pro 0813 | DeepSeek | 51% | $0.66 Routed quote | $1.98 Routed quote | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 50 | DeepSeek V4 Pro 0423 | DeepSeek | 51% | $0.435 via Tencent | $0.87 via Tencent | |||||||||||||||||||||||||||||
1–50 of 464
Page 1 of 10
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower. Cost per task uses best-effort token usage. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
Frequently asked questions
What is the SciCode benchmark?
A research coding benchmark curated by scientists across 16 natural-science sub-fields, where models write Python to solve real scientific problems. Its 80 main problems decompose into 338 subproblems, graded against scientist-annotated gold solutions and test cases.
Which AI model scores highest on SciCode?
Claude Opus 5.5 (Anthropic) leads with 67%, from $4.00 per 1M input tokens from Anthropic.
How many models are ranked on SciCode?
145 models carry a SciCode score. Scores come from Artificial Analysis; where a model has a listed API price it is drawn from LiteLLM and OpenRouter, and models with no current price are listed without one.
Other benchmarks
compare the same models on a different evalIntelligence Indexcomposite indexCoding Indexcomposite indexAgentic Indexcomposite indexGPQA DiamondleaderboardHumanity's Last ExamleaderboardMMLU-ProleaderboardMMMU-ProleaderboardLiveCodeBenchleaderboardTerminalBench HardleaderboardTerminalBench v2.1leaderboardτ²-benchleaderboardτ-bench BankingleaderboardAPEX AgentsleaderboardIT-Bench SREleaderboardGDPvalleaderboardCritPtleaderboardOmniscienceleaderboardIFBenchleaderboardLong-Context Reasoningcomposite indexSWE-bench VerifiedleaderboardSWE-bench ProleaderboardAIME 2026leaderboardARC-AGI-2leaderboardAA-Briefcaseleaderboard
Benchmark scores via Artificial Analysis · scores updated Oct 14, 2026 · Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 156 prices older, back to Jul 19, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI