BigCodeReward: leaderboard
Each model acts as a judge on all 4,731 BigCodeArena conversations: given the user prompts, two models' code responses and their execution outputs (logs and screenshots), it says which response is better or that they tie. The score is agreement with the human vote; unlike reward benchmarks on text-only code, the judge sees what the code did when run.
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Not forecast. 12 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 72B Instruct | 66.2 | #849 |
| 2 | GPT-4o Mini (2024-07-18) | 64.5 | #1494 |
| 3 | Claude Sonnet 4 (20250514) | 62.3 | #405 |
| 4 | Claude 3.7 Sonnet (20250219) | 62.2 | #421 |
| 5 | Qwen 2.5 VL 32B Instruct | 61.9 | #1074 |
| 6 | Gemma 3 27B (IT) | 61.1 | #1339 |
| 7 | GPT-4.1 (2025-04-14) | 60 | #501 |
| 8 | GLM-4.5V | 55.2 | #758 |
| 9 | MiMo-VL-7B-RL | 50.7 | #1162 |
| 10 | InternVL3-38B | 48 | #927 |
| 11 | InternVL3-78B | 46.8 | #755 |
| 12 | Kimi-VL-A3B-Thinking-2506 | 46.2 | #1599 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=bigcodereward · How It Works · Data refreshed daily, snapshot 2026-11-17.