A continuously updated benchmark that uses difficult problems from competitive-programming platforms to evaluate coding ability while reducing data contamination.
Browse the latest scores, model modes, release dates, and parameter sizes for LiveCodeBench.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 DeepSeek-V4-Pro Thinking Level · Max | 93.50 | 2026-04-24 | 1600B | Free Commercial | |
 Gemini 3.0 Pro (Preview 11-2025) Thinking Enabled | 92.00 | 2025-11-18 | Unknown | Closed | |
Gemini 3.1 Pro Preview Thinking Level · HighTools | 91.70 | 2026-02-20 | Unknown | Closed | |
4 | DeepSeek-V4-Flash Thinking Level · Max | 91.60 | 2026-04-24 | 284B | Free Commercial |
5 |  Qwen3.7-Max-Preview Thinking Level · Max | 91.60 | 2026-05-20 | Unknown | Closed |
6 | DeepSeek-V4-Pro Thinking Level · High | 89.80 | 2026-04-24 | 1600B | Free Commercial |
7 |  Kimi K2.6 Thinking Enabled | 89.60 | 2026-04-20 | 1000B | Free Commercial |
8 | DeepSeek-V4-Flash Thinking Level · High | 88.40 | 2026-04-24 | 284B | Free Commercial |
9 | Gemini 2.5 Deep Think Deep Thinking Mode | 87.60 | 2025-08-01 | Unknown | Closed |
10 | Qwen 3.6 Plus Preview Thinking Enabled | 87.10 | 2026-03-31 | Unknown | Closed |
11 | Qwen3.6-Max-Preview Thinking Level · Max | 87.10 | 2026-04-18 | Unknown | Closed |
12 |  Opus 4.5 Extended ThinkingTools | 87.00 | 2025-11-25 | Unknown | Closed |
13 |  Step 3.5 Flash Thinking Enabled | 86.40 | 2026-02-02 | 196B | Free Commercial |
14 | Qwen3-Max-Thinking Thinking Enabled | 85.90 | 2026-01-26 | 1000B | Closed |
15 |  GPT-5.1 Codex Thinking Level · HighTools | 85.50 | 2025-11-14 | Unknown | Closed |
16 | Kimi K2.5 Thinking Enabled | 85.00 | 2026-01-27 | 1000B | Free Commercial |
17 |  GLM-4.7 Thinking Enabled | 84.90 | 2025-12-22 | 358B | Free Commercial |
18 | GLM-4.6 Thinking EnabledTools | 84.50 | 2025-09-30 | 355B | Free Commercial |
19 | Qwen3.6-27B Thinking Enabled | 83.90 | 2026-04-22 | 27B | Free Commercial |
20 | Qwen3.5-397B-A17B Thinking Enabled | 83.60 | 2026-02-16 | 39.7B | Free Commercial |
21 | DeepSeek V3.2 Thinking Enabled | 83.30 | 2025-12-01 | 671B | Free Commercial |
22 | Kimi K2 Thinking Thinking Enabled | 83.10 | 2025-11-06 | 1040B | Free Commercial |
23 |  MiniMax M2 Thinking Enabled | 83.00 | 2025-10-27 | 230B | Free Commercial |
24 | GLM-4.6 Thinking Enabled | 82.80 | 2025-09-30 | 355B | Free Commercial |
25 |  Grok 4 Thinking Enabled | 82.00 | 2025-07-10 | Unknown | Closed |
26 | Grok 4.1 Fast Thinking Enabled | 82.00 | 2025-11-19 | Unknown | Closed |
27 | Qwen3.5-27B Thinking EnabledTools | 80.70 | 2026-02-25 | 27B | Free Commercial |
28 | Gemini 2.5 Pro Deep Think Standard Mode | 80.40 | 2025-06-17 | Unknown | Closed |
29 | Qwen3.6-35B-A3B Thinking Enabled | 80.40 | 2026-04-16 | 35B | Free Commercial |
30 | Grok 4 Fast Thinking Enabled | 80.00 | 2025-09-19 | Unknown | Closed |
