LiveCodeBench (Artificial Analysis run) leaderboard
- models measured
- 84
- lead over #2
- +1.4 pts
- median
- 51.4%
Leader on LiveCodeBench (Artificial Analysis run) · read October 21
# LiveCodeBench (Artificial Analysis run), read October 21
leaders = {
"Gemini 3 Flash Preview": 90.8%, "GPT-5.2": 89.4%, "GLM 4.7": 89.4%,
}
On October 21, 2026, 87 of our catalog's models had a LiveCodeBench (Artificial Analysis run) result, and Google Gemini 3 Flash Preview led with 90.8%, ahead of OpenAI GPT-5.2 at 89.4%.
Competitive programming problems collected after the models were trained. Share solved. 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 | Gemini 3 Flash PreviewGoogle | 90.8% | 43.7 | $3.00 | |
| 2 | GPT-5.2OpenAI | 89.4% | 55.9 | $14.00 | |
| 3 | GLM 4.7Z.ai | 89.4% | 55.1 | $2.20 | |
| 4 | gpt-oss-120bOpenAI | 87.8% | Not benchmarked | $0.50 | |
| 5 | Claude Opus 4.5Anthropic | 87.1% | 44.0 | $25.00 | |
| 6 | GPT-5.1OpenAI | 86.8% | 40.4 | $10.00 | |
| 7 | DeepSeek V3.2DeepSeek | 86.2% | 30.0 | $0.88 | |
| 8 | o4 MiniOpenAI | 85.9% | Not benchmarked | $4.40 | |
| 9 | Kimi K2 ThinkingMoonshot AI | 85.3% | Not benchmarked | $2.50 | |
| 10 | GPT-5.1-CodexOpenAI | 84.9% | 15.3 | $10.00 | |
| 11 | GPT-5OpenAI | 84.6% | 38.8 | $10.00 | |
| 12 | GPT-5 MiniOpenAI | 83.8% | 34.2 | $2.00 | |
| 13 | GPT-5.1-Codex-MiniOpenAI | 83.6% | Not benchmarked | $2.00 | |
| 14 | MiniMax M2MiniMax | 82.6% | Not benchmarked | $1.02 | |
| 15 | MiniMax M2.1MiniMax | 81.0% | Not benchmarked | $1.20 | |
| 16 | o3OpenAI | 80.8% | Not benchmarked | $8.00 | |
| 17 | Gemini 2.5 ProGoogle | 80.1% | 19.1 | $10.00 | |
| 18 | DeepSeek V3.1 TerminusDeepSeek | 79.8% | Not benchmarked | $1.0142 | |
| 19 | DeepSeek V3.2 ExpDeepSeek | 78.9% | Not benchmarked | $0.41 | |
| 20 | GPT-5 NanoOpenAI | 78.9% | Not benchmarked | $0.40 | |
| 21 | Qwen3 235B A22B Instruct 2507Qwen | 78.8% | Not benchmarked | $0.75 | |
| 22 | Qwen3 Next 80B A3B InstructQwen | 78.4% | Not benchmarked | $1.10 | |
| 23 | Gemini 2.5 Pro Preview 06-05Google | 77.8% | Not benchmarked | $10.00 | |
| 24 | gpt-oss-20bOpenAI | 77.7% | Not benchmarked | $0.15 | |
| 25 | R1 0528DeepSeek | 77.0% | Not benchmarked | $2.18 | |
| 26 | Nemotron 3 Nano 30B A3BNVIDIA | 74.1% | Not benchmarked | $0.22 | |
| 27 | GLM 4.5Z.ai | 73.8% | Not benchmarked | $2.20 | |
| 28 | o3 MiniOpenAI | 73.4% | Not benchmarked | $4.40 | |
| 29 | Qwen3 30B A3B Instruct 2507Qwen | 70.7% | Not benchmarked | $0.30 | |
| 30 | Qwen3 VL 30B A3B InstructQwen | 69.7% | Not benchmarked | $0.70 | |
| 31 | Gemini 2.5 FlashGoogle | 69.5% | Not benchmarked | $2.50 | |
| 32 | GLM 4.6Z.ai | 69.5% | 8.8 | $2.20 | |
| 33 | GLM 4.5 AirZ.ai | 68.4% | Not benchmarked | $1.10 | |
| 34 | o1OpenAI | 67.9% | Not benchmarked | $60.00 | |
| 35 | Qwen3 VL 235B A22B InstructQwen | 64.6% | Not benchmarked | $1.90 | |
| 36 | Kimi K2 0905Moonshot AI | 61.0% | Not benchmarked | $2.50 | |
| 37 | GLM 4.5VZ.ai | 60.4% | Not benchmarked | $1.80 | |
| 38 | Gemini 2.5 Flash LiteGoogle | 59.3% | Not benchmarked | $0.40 | |
| 39 | Qwen3 Coder 480B A35BQwen | 58.5% | Not benchmarked | $1.50 | |
| 40 | o1-miniRetiredOpenAI | 57.6% | Not benchmarked | $4.40 | |
| 41 | Kimi K2 0711Moonshot AI | 55.6% | Not benchmarked | $2.30 | |
| 42 | Qwen3 32BQwen | 54.6% | Not benchmarked | $0.40 | |
| 43 | Qwen3 14BQwen | 52.3% | Not benchmarked | $0.23 | |
| 44 | Qwen3 30B A3BQwen | 50.6% | Not benchmarked | $0.50 | |
| 45 | GPT-4.1 MiniOpenAI | 48.3% | Not benchmarked | $1.60 | |
| 46 | GPT-4.1OpenAI | 45.7% | Not benchmarked | $8.00 | |
| 47 | Reka Flash 3Reka | 43.5% | Not benchmarked | $0.20 | |
| 48 | Grok 3RetiredxAI | 42.5% | Not benchmarked | $15.00 | |
| 49 | GLM 4.6VZ.ai | 41.1% | Not benchmarked | $0.90 | |
| 50 | Mistral Medium 3.1Mistral AI | 40.6% | Not benchmarked | $2.00 | |
| 51 | DeepSeek V3 0324DeepSeek | 40.5% | Not benchmarked | $1.07 | |
| 52 | Qwen3 Coder 30B A3B InstructQwen | 40.3% | Not benchmarked | $0.44 | |
| 53 | Mistral Medium 3Mistral AI | 40.0% | Not benchmarked | $2.00 | |
| 54 | Llama 4 MaverickMeta Llama | 39.7% | Not benchmarked | $1.00 | |
| 55 | Qwen3 VL 8B InstructQwen | 35.3% | Not benchmarked | $0.75 | |
| 56 | GPT-4o (2024-05-13)OpenAI | 33.4% | Not benchmarked | $15.00 | |
| 57 | GPT-4.1 NanoOpenAI | 32.6% | Not benchmarked | $0.40 | |
| 58 | Nova Premier 1.0Amazon | 31.7% | Not benchmarked | $12.50 | |
| 59 | GPT-4o (2024-08-06)OpenAI | 31.7% | Not benchmarked | $10.00 | |
| 60 | GPT-4oOpenAI | 30.9% | Not benchmarked | $10.00 | |
| 61 | Llama 4 ScoutMeta Llama | 29.9% | Not benchmarked | $0.50 | |
| 62 | SonarPerplexity | 29.5% | Not benchmarked | $1.00 | |
| 63 | Qwen2.5 Coder 32B InstructQwen | 29.5% | Not benchmarked | $1.00 | |
| 64 | GPT-4 TurboOpenAI | 29.1% | Not benchmarked | $30.00 | |
| 65 | Llama 3.3 70B InstructMeta Llama | 28.8% | Not benchmarked | $0.72 | |
| 66 | Command ACohere | 28.7% | Not benchmarked | $10.00 | |
| 67 | Qwen2.5 72B InstructQwen | 27.6% | Not benchmarked | $0.40 | |
| 68 | Sonar ProPerplexity | 27.5% | Not benchmarked | $15.00 | |
| 69 | Mistral Large 2407Mistral AI | 26.7% | Not benchmarked | $6.00 | |
| 70 | Grok 2RetiredxAI | 26.7% | Not benchmarked | $10.00 | |
| 71 | Mistral Small 3Mistral AI | 25.2% | Not benchmarked | $0.08 | |
| 72 | GPT-4o-miniOpenAI | 23.4% | Not benchmarked | $0.60 | |
| 73 | Nova Pro 1.0Amazon | 23.3% | Not benchmarked | $3.20 | |
| 74 | Llama 3.1 70B InstructMeta Llama | 23.2% | Not benchmarked | $0.56 | |
| 75 | Phi 4Microsoft | 23.1% | Not benchmarked | $0.14 | |
| 76 | N Hermes 3 70B InstructNous Research | 18.8% | Not benchmarked | $0.70 | |
| 77 | Granite 4.0 MicroIBM Granite | 18.0% | Not benchmarked | $0.112 | |
| 78 | Mistral LargeMistral AI | 17.8% | Not benchmarked | $6.00 | |
| 79 | Nova Lite 1.0Amazon | 16.7% | Not benchmarked | $0.24 | |
| 80 | Mixtral 8x22B InstructMistral AI | 14.8% | Not benchmarked | $6.00 | |
| 81 | Nova Micro 1.0Amazon | 14.0% | Not benchmarked | $0.14 | |
| 82 | Gemma 3 12BGoogle | 13.7% | Not benchmarked | $0.1625 | |
| 83 | Gemma 3 27BGoogle | 13.7% | Not benchmarked | $0.30 | |
| 84 | Llama 3.1 8B InstructMeta Llama | 11.6% | Not benchmarked | $0.08 | |
| 85 | Gemma 3 4BGoogle | 11.2% | Not benchmarked | $0.075 | |
| 86 | Llama 3.2 3B InstructMeta Llama | 8.3% | Not benchmarked | $0.3325 | |
| 87 | Llama 3.2 1B InstructMeta Llama | 1.9% | Not benchmarked | $0.201 |
Only models in our catalog are listed, and each appears once with its best published run. 198 rows were read from the source on October 21, 2026, and rows that match no catalog model are left out.