01/05/2025
31/05/2025
012345678910
40 problems from 32 repositories selected within the current time window.
You can adjust time window, modifying the problems' release start and end dates. Evaluations highlighted in red may be potentially contaminated, meaning they include tasks that were created before the model's release date. If a selected time window is wider than the range of task dates a model was evaluated on, the model will appear at the bottom of the leaderboard with N/A values.
Rank
Model
Resolved Rate (%)
Resolved Rate SEM (±)
pass@5 (%)
1
Claude Sonnet 4
56.5%1.87%62.5%
2
o3-2025-04-16
49.0%1.27%67.5%
3
gpt-4.1-2025-04-14
42.5%1.37%60.0%
4
gpt-4.1-2025-04-14
41.5%2.03%55.0%
5
gemini-2.5-flash-preview-05-20 no-thinking
41.0%1.87%57.5%
6
DeepSeek-V3-0324
38.0%1.66%52.5%
7
Claude Sonnet 3.5
37.0%1.66%52.5%
8
DeepSeek-V3
36.0%0.61%47.5%
9
gpt-4.1-mini-2025-04-14
35.5%2.55%50.0%
10
DeepSeek-V3-0324
34.0%0.61%52.5%
11
gemini-2.5-flash-preview-05-20 no-thinking
31.0%3.02%50.0%
12
Qwen3-235B-A22B no-thinking
27.5%2.24%50.0%
13
Qwen3-32B thinking
24.0%2.81%42.5%
14
Qwen3-235B-A22B thinking
23.5%2.81%47.5%
15
Devstral-Small-2505
23.0%0.94%52.5%
16
Qwen3-32B no-thinking
22.0%1.46%40.0%
17
Llama-3.3-70B-Instruct
21.0%2.57%45.0%
18
Llama-4-Maverick-17B-128E-Instruct
16.5%1.00%42.5%
19
Qwen2.5-72B-Instruct
16.0%1.50%35.0%
20
gemini-2.0-flash
12.5%1.12%27.5%
21
gemma-3-27b-it
9.5%1.46%20.0%
22
Llama-4-Scout-17B-16E-Instruct
8.5%1.50%20.0%
23
Qwen2.5-Coder-32B-Instruct
7.5%1.58%27.5%
24
gpt-4.1-nano-2025-04-14
0.5%0.50%2.5%

News

  • [2025-06-12]: Added tool usage support, evaluations on May data and new models: Claude Sonnet 3.5/4 and o3
  • [2025-05-22]: Added Devstral-Small-2505 to the leaderboard.
  • [2025-05-21]: Added new models to the leaderboard: gpt-4.1-mini-2025-04-14, gpt-4.1-nano-2025-04-14, gemini-2.0-flash and gemini-2.5-flash-preview-05-20.