A task with its own rules.
A display-only Artificial Analysis coding index.
- Organisation
- Artificial Analysis
- Version
- 2026
Loading benchmark header
Loading benchmark registry
Coding / Benchmark profile
A display-only Artificial Analysis coding index.
Observed results
20 ranked models · higher is better · labels show rank and score
| Model | Rank | Model ID | Provider | Score | Unit |
|---|---|---|---|---|---|
| Claude Opus 5 | #1 | claude-opus-5 | Anthropic | 77.98 | index |
| GPT-5.6 Sol | #2 | gpt-5-6-sol | OpenAI | 77.39 | index |
| GPT-5.6 Terra | #3 | gpt-5-6-terra | OpenAI | 76.66 | index |
| Claude Fable 5 | #4 | claude-fable-5 | Anthropic | 76.49 | index |
| Kimi K3 | #5 | kimi-k3 | Moonshot AI | 76.24 | index |
| GPT-5.5 | #6 | gpt-5-5 | OpenAI | 74.89 | index |
| Claude Opus 4.8 | #7 | claude-opus-4-8 | Anthropic | 74.25 | index |
| Claude Opus 4.7 | #8 | claude-opus-4-7 | Anthropic | 73.6 | index |
| Grok 4.5 | #9 | grok-4-5 | xAI | 72.45 | index |
| Claude Sonnet 5 | #10 | claude-sonnet-5 | Anthropic | 71.55 | index |
| GPT-5.6 Luna | #11 | gpt-5-6-luna | OpenAI | 71.45 | index |
| Muse Spark 1.1 | #12 | muse-spark-1-1 | Meta | 71.34 | index |
| GPT-5.4 | #13 | gpt-5-4 | OpenAI | 71.05 | index |
| Gemini 3.5 Flash | #14 | gemini-3-5-flash | 70.14 | index | |
| Gemini 3.6 Flash | #15 | gemini-3-6-flash | 69.24 | index | |
| GLM-5.2 | #16 | glm-5-2 | Z.AI | 68.76 | index |
| Qwen3.7-Max | #17 | qwen-3-7-max | Alibaba Cloud | 65.97 | index |
| Kimi K2.6 | #18 | kimi-k2-6 | Moonshot AI | 61.77 | index |
| Kimi K2.7 Code | #19 | kimi-k2-7-code | Moonshot AI | 60.76 | index |
| MiMo-V2.5-Pro | #20 | mimo-v2-5-pro | Xiaomi | 60.19 | index |
| DeepSeek V4 Pro | #21 | deepseek-v4-pro | DeepSeek | 59.36 | index |
| Hy3 | #22 | hy3 | Tencent | 58.8 | index |
| Hy3 Preview | #23 | hy3-preview | Tencent | 58.8 | index |
| Muse Spark | #24 | muse-spark | Meta | 58.62 | index |
| MiniMax M3 | #25 | minimax-m3 | MiniMax | 58.57 | index |
| DeepSeek V4 Flash | #26 | deepseek-v4-flash | DeepSeek | 56.17 | index |
| GPT-5.4 mini | #27 | gpt-5-4-mini | OpenAI | 56.08 | index |
| GPT-5.4 nano | #28 | gpt-5-4-nano | OpenAI | 56.07 | index |
| Qwen3.7-Plus | #29 | qwen-3-7-plus | Alibaba Cloud | 55.86 | index |
| GLM-5.1 | #30 | glm-5-1 | Z.AI | 55.78 | index |
| Qwen3.6 Plus | #31 | qwen3-6-plus | Alibaba Cloud | 54.53 | index |
| Qwen3.6 27B | #32 | qwen3-6-27b | Alibaba Cloud | 53.72 | index |
| MiniMax M2.7 | #33 | minimax-m2-7 | MiniMax | 52.62 | index |
| Inkling | #34 | inkling | Thinking Machines Lab | 52.06 | index |
| GPT-5.1 | #35 | gpt-5-1 | OpenAI | 49.39 | index |
| Gemini 3.5 Flash-Lite | #36 | gemini-3-5-flash-lite | 49.32 | index | |
| Nemotron 3 Ultra | #37 | nemotron-3-ultra | NVIDIA | 49.27 | index |
| Qwen3.5 397B A17B | #38 | qwen3-5-397b | Alibaba Cloud | 48.21 | index |
| Mistral Medium 3.5 128B | #39 | mistral-medium-3-5-128b | Mistral AI | 46.9 | index |
| Kimi K2.5 | #40 | kimi-k2-5 | Moonshot AI | 46.78 | index |
| Qwen3.5-122B-A10B | #41 | qwen3-5-122b-a10b | Alibaba Cloud | 45.71 | index |
| GLM-4.7 | #42 | glm-4-7 | Z.AI | 45.26 | index |
| Gemma 4 31B | #43 | gemma-4-31b | 43.43 | index | |
| Grok 4.3 | #44 | grok-4-3 | xAI | 42.25 | index |
| Qwen3.6-35B-A3B | #45 | qwen3-6-35b-a3b | Alibaba Cloud | 41.88 | index |
| o1 | #46 | o1 | OpenAI | 39.72 | index |
| Step 3.7 Flash | #47 | step-3-7-flash | StepFun | 39.57 | index |
| Gemma 4 26B A4B | #48 | gemma-4-26b-a4b | 39.32 | index | |
| GPT-5 | #49 | gpt-5 | OpenAI | 37.78 | index |
| Gemini 3.1 Flash-Lite | #50 | gemini-3-1-flash-lite | 34.69 | index | |
| o1-preview | #51 | o1-preview | OpenAI | 34.05 | index |
| Gemini 2.5 Pro | #52 | gemini-2-5-pro | 33.25 | index | |
| K-Exaone | #53 | k-exaone | LG AI Research | 32.11 | index |
| Gemma 4 12B Unified | #54 | gemma-4-12b | 30.96 | index | |
| GPT-OSS 120B | #55 | gpt-oss-120b | OpenAI | 30.44 | index |
| Command A+ | #56 | command-a-plus | Cohere | 27.85 | index |
| Mistral Small 4 | #57 | mistral-small-4 | Mistral AI | 26.64 | index |
| Trinity-Large-Preview | #58 | trinity-large-preview | Arcee AI | 25.77 | index |
| Trinity-Large-Thinking | #59 | trinity-large-thinking | Arcee AI | 25.77 | index |
| Ling 2.6 Flash | #60 | ling-2-6-flash | InclusionAI | 25.26 | index |
| Gemini 1.5 Pro | #61 | gemini-1-5-pro | 23.63 | index | |
| DeepSeek V3 | #62 | deepseek-v3 | DeepSeek | 23.04 | index |
| GPT-4 Turbo | #63 | gpt-4-turbo | OpenAI | 21.49 | index |
| GPT-OSS 20B | #64 | gpt-oss-20b | OpenAI | 20.7 | index |
| GPT-4.1 mini | #65 | gpt-4-1-mini | OpenAI | 20.21 | index |
| Mistral Large 3 | #66 | mistral-large-3 | Mistral AI | 20.07 | index |
| Claude 3 Opus | #67 | claude-3-opus | Anthropic | 19.53 | index |
| Llama 4 Maverick | #68 | llama-4-maverick | Meta | 16.28 | index |
| Nemotron 3 Nano 30B | #69 | nemotron-3-nano-30b | NVIDIA | 14.37 | index |
| Nemotron 3 Nano Omni 30B A3B | #70 | nemotron-3-nano-omni-30b-a3b | NVIDIA | 13.75 | index |
| GPT-4o mini | #71 | gpt-4o-mini | OpenAI | 11.38 | index |
| GPT-4.1 nano | #72 | gpt-4-1-nano | OpenAI | 11.14 | index |
| Gemma 3 27B | #73 | gemma-3-27b | 10.06 | index | |
| Gemma 4 E4B | #74 | gemma-4-e4b | 9.39 | index | |
| Llama 4 Scout | #75 | llama-4-scout | Meta | 8.17 | index |
| Gemma 4 E2B | #76 | gemma-4-e2b | 7.23 | index |
One best compatible score per canonical product · higher is better
| Rank | Model | Weights | Evidence | Score |
|---|---|---|---|---|
| 01 | Claude Opus 5Anthropic | Closed weights | Source carrier | 78.0 index |
| 02 | GPT-5.6 SolOpenAI | Closed weights | Source carrier | 77.4 index |
| 03 | GPT-5.6 TerraOpenAI | Closed weights | Source carrier | 76.7 index |
| 04 | Claude Fable 5Anthropic | Closed weights | Source carrier | 76.5 index |
| 05 | Kimi K3Moonshot AI | Open weights | Source carrier | 76.2 index |
| 06 | GPT-5.5OpenAI | Closed weights | Source carrier | 74.9 index |
| 07 | Claude Opus 4.8Anthropic | Closed weights | Source carrier | 74.3 index |
| 08 | Claude Opus 4.7Anthropic | Closed weights | Source carrier | 73.6 index |
| 09 | Grok 4.5xAI | Closed weights | Source carrier | 72.5 index |
| 10 | Claude Sonnet 5Anthropic | Closed weights | Source carrier | 71.5 index |
Each distinct published measurement is retained. Same-snapshot canonical and configuration projections appear once.
| Published model / configuration | Score | Evidence & protocol | Source & dates |
|---|---|---|---|
Exact BenchLM registry variant Claude Opus 5; bulk export does not retain a complete upstream harness configuration.Claude Opus 5Exact identitySource label without a registered configuration ID Canonical product: claude-opus-5 | 78.0 index | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GPT-5.6 Sol; bulk export does not retain a complete upstream harness configuration.GPT-5.6 SolExact identitySource label without a registered configuration ID Canonical product: gpt-5-6-sol | 77.4 index | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GPT-5.6 Terra; bulk export does not retain a complete upstream harness configuration.GPT-5.6 TerraExact identitySource label without a registered configuration ID Canonical product: gpt-5-6-terra | 76.7 index | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Fable 5; bulk export does not retain a complete upstream harness configuration.Claude Fable 5Exact identitySource label without a registered configuration ID Canonical product: claude-fable-5 | 76.5 index | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Kimi K3; bulk export does not retain a complete upstream harness configuration.Kimi K3Exact identitySource label without a registered configuration ID Canonical product: kimi-k3 | 76.2 index | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GPT-5.5; bulk export does not retain a complete upstream harness configuration.GPT-5.5Exact identitySource label without a registered configuration ID Canonical product: gpt-5-5 | 74.9 index | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Opus 4.8; bulk export does not retain a complete upstream harness configuration.Claude Opus 4.8Exact identitySource label without a registered configuration ID Canonical product: claude-opus-4-8 | 74.3 index | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Opus 4.7 (Adaptive); bulk export does not retain a complete upstream harness configuration.Claude Opus 4.7Exact identityclaude-opus-4-7-max Canonical product: claude-opus-4-7 | 73.6 index | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Grok 4.5; bulk export does not retain a complete upstream harness configuration.Grok 4.5Exact identitySource label without a registered configuration ID Canonical product: grok-4-5 | 72.5 index | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Sonnet 5; bulk export does not retain a complete upstream harness configuration.Claude Sonnet 5Exact identitySource label without a registered configuration ID Canonical product: claude-sonnet-5 | 71.5 index | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
From result to context
A display-only Artificial Analysis coding index.
The summary shows one best compatible source result per canonical product. Versions, effort settings and execution systems remain attached to the underlying records.
Scores from different versions or harnesses may not be interchangeable. The published source rows preserve those distinctions and their original units. A source result is not automatically an input to a current index.
This catalogue entry preserves available source evidence. Current indices admit only their specifically reviewed tracks and configurations.
Contamination risk: Unknown. Lifecycle: Active.