Terminal-Bench 4.0 (Artificial Analysis run) leaderboard
- Kimi K3.1 Pro leads
- 67.2%
- models measured
- 111
- lead over #2
- +2.0 pts
- median
- 3.0%
Leader on Terminal-Bench 4.0 (Artificial Analysis run) · read November 14
# Terminal-Bench 4.0 (Artificial Analysis run), read November 14
leaders = {
"Kimi K3.1 Pro": 67.2%, "Gemini 4 Carbon": 65.2%, "Claude Sonnet 5.5": 63.6%,
}
On November 14, 2026, 117 of our catalog's models had a Terminal-Bench 4.0 (Artificial Analysis run) result, and MoonshotAI Kimi K3.1 Pro led with 67.2%, ahead of Google Gemini 4 Carbon at 65.2%.
Version 4.0 of Terminal-Bench: tasks finished in a real terminal. Share completed. Run by Artificial Analysis on its own harness.
Role in the index
A coding board we show beside the Vibe Coding Index, not inside it: the index keeps the six boards it was defined on, so a score does not move every time a board is added. Read the methodology
| # | Model | Result | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Kimi K3.1 ProMoonshot AI | 67.2% | 79.0 | $10.00 | |
| 2 | Gemini 4 CarbonGoogle | 65.2% | 86.6 | $10.00 | |
| 3 | Claude Sonnet 5.5Anthropic | 63.6% | 84.3 | $10.00 | |
| 4 | Claude Fable 5.2Anthropic | 61.6% | 87.8 | $40.00 | |
| 5 | Claude Opus 5.5Anthropic | 59.6% | 87.3 | $20.00 | |
| 6 | GPT-6 AstraOpenAI | 59.6% | 83.8 | $50.00 | |
| 7 | Gemini 4 ArgonGoogle | 57.1% | 80.3 | $10.00 | |
| 8 | GPT-6.1 SolOpenAI | 56.1% | 79.8 | $10.00 | |
| 9 | GPT-6.1 TerraOpenAI | 55.6% | 76.4 | $5.00 | |
| 10 | Claude Fable 5.1Anthropic | 55.1% | 82.8 | $50.00 | |
| 11 | Gemini 4 HydrogenGoogle | 54.0% | 77.9 | $7.50 | |
| 12 | Muse WonderMeta | 52.0% | 71.8 | $20.00 | |
| 13 | Claude Opus 5Anthropic | 49.0% | 81.7 | $25.00 | |
| 14 | GPT-6 SolOpenAI | 43.9% | 72.1 | $10.00 | |
| 15 | Claude Fable 5Anthropic | 42.4% | 75.9 | $50.00 | |
| 16 | GLM 5.3Z.ai | 41.9% | 68.5 | $4.40 | |
| 17 | Muse EmberMeta | 40.9% | 64.9 | $0.50 | |
| 18 | GPT-5.6 SolOpenAI | 39.9% | 70.6 | $20.00 | |
| 19 | Qwen3.8 Max (0902)Qwen | 38.9% | 67.3 | $6.00 | |
| 20 | Hy4Tencent | 37.4% | 65.2 | $1.2505 | |
| 21 | GPT-5.6 TerraOpenAI | 35.4% | 63.5 | $12.00 | |
| 22 | MiMo-V2.6-ProXiaomi | 34.8% | 61.8 | $0.87 | |
| 23 | DeepSeek V4.1 Flash 1017DeepSeek | 33.8% | 66.9 | $0.60 | |
| 24 | Ling 3.1 FlashinclusionAI | 33.3% | Not benchmarked | $0.135 | |
| 25 | Muse Spark 1.3Meta | 33.3% | 56.1 | $4.25 | |
| 26 | Step 5 PreviewStepFun | 33.3% | 57.4 | $2.70 | |
| 27 | Claude Haiku 5.5Anthropic | 32.8% | 68.4 | $0.50 | |
| 28 | GLM 5.3 FlashZ.ai | 32.8% | 56.2 | $0.50 | |
| 29 | DeepSeek V4.1 FlashDeepSeek | 26.8% | 56.6 | $0.79 | |
| 30 | MiniMax M3.1 FlashMiniMax | 25.8% | 55.7 | $0.60 | |
| 31 | Grok 4.7xAI | 25.8% | 64.8 | $6.00 | |
| 32 | Mistral Large 4Mistral AI | 24.7% | 60.9 | $2.10 | |
| 33 | MiMo-V2.6-FlashXiaomi | 22.7% | 54.8 | $0.28 | |
| 34 | Claude Opus 4.8Anthropic | 21.7% | 62.8 | $25.00 | |
| 35 | Grok 4.6xAI | 21.2% | 63.9 | $6.00 | |
| 36 | Gemini 3.8 FlashGoogle | 19.7% | 60.3 | $3.75 | |
| 37 | GPT-5.5OpenAI | 14.6% | 67.9 | $30.00 | |
| 38 | Claude Sonnet 5Anthropic | 14.1% | 54.6 | $10.00 | |
| 39 | DeepSeek V4 Pro 0813DeepSeek | 14.1% | 56.1 | $1.98 | |
| 40 | Gemini 3.7 FlashGoogle | 13.6% | 53.9 | $3.75 | |
| 41 | T Inkling 2 SmallThinking Machines | 13.1% | 48.9 | $1.00 | |
| 42 | Kimi K3Moonshot AI | 12.6% | 61.4 | $15.00 | |
| 43 | GPT-6 LunaOpenAI | 12.6% | 54.9 | $0.50 | |
| 44 | DeepSeek V4 Flash 0731DeepSeek | 12.1% | 51.8 | $0.348 | |
| 45 | DeepSeek V4 Flash Vision ExpDeepSeek | 12.1% | Not benchmarked | $0.9834 | |
| 46 | GPT-5.6 LunaOpenAI | 11.6% | 55.3 | $1.20 | |
| 47 | Qwen3.8 2.4T A95BQwen | 11.1% | Not benchmarked | $6.00 | |
| 48 | Grok 4.5xAI | 10.6% | 52.3 | $6.00 | |
| 49 | Muse Spark OpenMeta | 8.1% | 43.4 | $4.25 | |
| 50 | Gemini 3.6 FlashGoogle | 7.1% | 62.5 | $3.75 | |
| 51 | Muse Spark 1.2Meta | 7.1% | 50.9 | $4.25 | |
| 52 | Gemini 3.5 FlashGoogle | 6.6% | 39.8 | $9.00 | |
| 53 | Muse Spark 1.1Meta | 6.1% | 70.2 | $4.25 | |
| 54 | Qwen3.8 27BQwen | 5.6% | 69.7 | $2.55 | |
| 55 | Gemini 3.1 Pro PreviewGoogle | 4.0% | 32.3 | $12.00 | |
| 56 | Claude Sonnet 4.6Anthropic | 3.0% | 55.0 | $15.00 | |
| 57 | MiniMax M3MiniMax | 2.0% | 33.6 | $1.20 | |
| 58 | GPT-5.4 MiniOpenAI | 2.0% | 35.8 | $4.50 | |
| 59 | GLM 5.1Z.ai | 2.0% | 49.2 | $4.40 | |
| 60 | Qwen3.7 MaxQwen | 1.5% | 54.1 | $4.425 | |
| 61 | Gemini 3.5 Flash LiteGoogle | 1.0% | 48.9 | $2.50 | |
| 62 | Kimi K2.7 CodeMoonshot AI | 1.0% | 53.4 | $4.00 | |
| 63 | Qwen3.7 PlusQwen | 1.0% | 33.2 | $1.28 | |
| 64 | T InklingThinking Machines | 1.0% | 29.2 | $4.05 | |
| 65 | T Inkling SmallThinking Machines | 1.0% | 27.3 | $1.20 | |
| 66 | Solar Mini 4Upstage | 1.0% | Not benchmarked | $0.20 | |
| 67 | GLM 5.2Z.ai | 1.0% | 61.1 | $4.40 | |
| 68 | Trinity Large ThinkingRetiredArcee AI | 0.5% | Not benchmarked | $0.80 | |
| 69 | Command ACohere | 0.5% | Not benchmarked | $10.00 | |
| 70 | Gemini 3.1 Flash LiteGoogle | 0.5% | Not benchmarked | $1.50 | |
| 71 | Kimi K2.6Moonshot AI | 0.5% | 52.1 | $4.00 | |
| 72 | Nemotron 3 UltraNVIDIA | 0.5% | 30.0 | $2.30 | |
| 73 | Nemotron 3.5 LightningNVIDIA | 0.5% | 22.6 | $0.18 | |
| 74 | GPT-5.4 NanoOpenAI | 0.5% | 44.8 | $1.25 | |
| 75 | Qwen3.5-9BQwen | 0.5% | Not benchmarked | $0.15 | |
| 76 | Hy3Tencent | 0.5% | Not benchmarked | $0.528 | |
| 77 | DeepSeek V3 0324DeepSeek | 0.0% | Not benchmarked | $1.07 | |
| 78 | DeepSeek V3.1 TerminusDeepSeek | 0.0% | Not benchmarked | $1.00 | |
| 79 | Gemini 2.5 ProGoogle | 0.0% | 19.2 | $10.00 | |
| 80 | Gemma 3 12BGoogle | 0.0% | Not benchmarked | $0.15 | |
| 81 | Gemma 3 27BGoogle | 0.0% | Not benchmarked | $0.325 | |
| 82 | Gemma 4 31BGoogle | 0.0% | 21.9 | $0.40 | |
| 83 | Granite 4.2 8BIBM Granite | 0.0% | Not benchmarked | $0.20 | |
| 84 | Mercury 2RetiredInception | 0.0% | Not benchmarked | $0.75 | |
| 85 | Mercury 2.5RetiredInception | 0.0% | 1.6 | $0.15 | |
| 86 | Ling 3.0 FlashinclusionAI | 0.0% | 29.6 | $0.1215 | |
| 87 | Ling 3.0 Flash FinRetiredinclusionAI | 0.0% | Not benchmarked | $0.1232 | |
| 88 | Ling 3.0 Flash VLinclusionAI | 0.0% | Not benchmarked | $0.18 | |
| 89 | Ling 3.0 TinyinclusionAI | 0.0% | Not benchmarked | $0.045 | |
| 90 | LongCat 2.0Meituan | 0.0% | Not benchmarked | $1.20 | |
| 91 | Llama 4 MaverickMeta Llama | 0.0% | Not benchmarked | $1.075 | |
| 92 | Llama 4 ScoutMeta Llama | 0.0% | Not benchmarked | $0.50 | |
| 93 | MiniMax M2.7MiniMax | 0.0% | 36.2 | $1.32 | |
| 94 | Mistral Medium 3.1Mistral AI | 0.0% | Not benchmarked | $2.00 | |
| 95 | Mistral Medium 3.5Mistral AI | 0.0% | 25.4 | $7.50 | |
| 96 | Mistral Small 4Mistral AI | 0.0% | Not benchmarked | $0.60 | |
| 97 | Nemotron 3 Nano 30B A3BNVIDIA | 0.0% | Not benchmarked | $0.24 | |
| 98 | Nemotron 3 SuperNVIDIA | 0.0% | Not benchmarked | $0.425 | |
| 99 | Nemotron 3.5 Super VLNVIDIA | 0.0% | 14.8 | $0.50 | |
| 100 | GPT-5 MiniOpenAI | 0.0% | 34.2 | $2.00 | |
| 101 | gpt-oss-120bOpenAI | 0.0% | Not benchmarked | $0.45 | |
| 102 | gpt-oss-20bOpenAI | 0.0% | Not benchmarked | $0.14 | |
| 103 | o3 MiniRetiredOpenAI | 0.0% | Not benchmarked | $4.40 | |
| 104 | Qwen3 14BQwen | 0.0% | Not benchmarked | $0.23 | |
| 105 | Qwen3 235B A22B Instruct 2507Qwen | 0.0% | Not benchmarked | $0.675 | |
| 106 | Qwen3 30B A3B Instruct 2507Qwen | 0.0% | Not benchmarked | $0.30 | |
| 107 | Qwen3 32BQwen | 0.0% | Not benchmarked | $0.40 | |
| 108 | Qwen3 Coder NextQwen | 0.0% | Not benchmarked | $0.80 | |
| 109 | Qwen3.5 397B A17BQwen | 0.0% | Not benchmarked | $2.34 | |
| 110 | Qwen3.5-122B-A10BQwen | 0.0% | Not benchmarked | $2.08 | |
| 111 | Qwen3.6 27BQwen | 0.0% | 36.8 | $2.70 | |
| 112 | Qwen3.6 35B A3BQwen | 0.0% | Not benchmarked | $0.925 | |
| 113 | Grok 4.3xAI | 0.0% | 37.4 | $2.50 | |
| 114 | Solar Pro 3RetiredUpstage | 0.0% | Not benchmarked | $0.60 | |
| 115 | Solar Pro 4Upstage | 0.0% | Not benchmarked | $0.60 | |
| 116 | MiMo-V2.5Xiaomi | 0.0% | 50.0 | $2.00 | |
| 117 | MiMo-V2.5-ProXiaomi | 0.0% | 31.5 | $1.335 |
Only models in our catalog are listed, and each appears once with its best published run. 214 rows were read from the source on November 14, 2026, and rows that match no catalog model are left out.