MongoDB - Build AI That Scales
Mini toolsLiveCodeBench
Continuously refreshed competitive-programming problems sourced from LeetCode, AtCoder, and Codeforces after the model's knowledge cutoff. Designed to stay contamination-free.
Coding
Text
Accuracy
Max 100.0%
Released Mar 2024
26
Results
25
Models scored
93.5%
Top: Deepseek V4 Pro
70.6%
Median
Best results
Top primary scores; one row per model.
Frontier over time
Each dot is one model result; the line traces the running best score.
All results
Showing all configurations including non-primary alternates. · Show only primary
| # | Model | Score | Conditions | Eval date | Source | Flags |
|---|---|---|---|---|---|---|
| 1 | Deepseek V4 Pro | 93.5% | 0-shot · CoT · Think High/Max mode | 24 Apr 2026 | Self-reported | Primary Verified |
| 2 | Qwen 3.7 Max | 91.6% | 0-shot · CoT · standard | 20 May 2026 | Self-reported | |
| 3 | Kimi K2.6 | 89.6% | CoT | 20 Apr 2026 | Self-reported | Primary |
| 4 | Kimi K2.5 | 85.0% | CoT | 27 Jan 2026 | Self-reported | Primary |
| 5 | Deepseek 3.2 | 83.3% | CoT · Pass@1 | 01 Dec 2025 | Paper | Primary Verified |
| 6 | GLM 4.6 | 82.8% | CoT | 30 Sep 2025 | Self-reported | Primary |
| 7 | Gemma 4 | 80.0% | CoT | 03 Apr 2026 | Self-reported | Primary |
| 8 | Grok 3 Think | 79.4% | CoT | 19 Feb 2025 | Self-reported | Primary |
| 9 | Grok 4 Heavy | 79.4% | — | 07 Sep 2025 | Self-reported | Primary |
| 10 | Grok 4 | 79.0% | — | 09 Jul 2025 | Self-reported | Primary |
| 11 | DeepSeek V3.1 Terminus | 74.9% | — | 22 Sep 2025 | Self-reported | Primary |
| 12 | DeepSeek V3.2 Exp | 74.1% | CoT | 29 Sep 2025 | Self-reported | Primary |
| 13 | Qwen3-235B-A22B | 70.7% | CoT | 28 Apr 2025 | Self-reported | Primary |
| 14 | Qwen3 235B A22B | 70.7% | — | 28 Apr 2025 | Self-reported | Primary |
| 15 | Gemini 2.5 Pro | 70.4% | — | 17 Jun 2025 | Third-party | Primary Verified |
| 16 | Nemotron 3 Nano | 68.3% | — | 15 Dec 2025 | Self-reported | Primary |
| 17 | Qwen3 30B A3B | 62.6% | — | 28 Apr 2025 | Self-reported | Primary |
| 18 | Grok 3 | 57.0% | — | 19 Feb 2025 | Self-reported | Primary |
| 19 | Grok 3 | 57.0% | — | 19 Feb 2025 | Self-reported | Primary |
| 20 | Kimi K2 Instruct | 53.7% | — | 02 Jul 2025 | Paper | Primary |
| 21 | Magistral Medium | 50.3% | CoT | 10 Jun 2025 | Self-reported | Primary |
| 22 | Llama 4 Behemoth | 49.4% | — | 05 Apr 2025 | Self-reported | Primary |
| 23 | Llama 4 Maverick | 43.4% | — | 05 Apr 2025 | Self-reported | Primary |
| 24 | Grok 3 mini | 41.5% | — | 19 Feb 2025 | Self-reported | Primary |
| 25 | Gemini 2.0 Flash | 34.5% | 0-shot · standard | 05 Feb 2025 | Self-reported | |
| 26 | Mistral Large 3 | 34.4% | — | 02 Dec 2025 | Self-reported | Primary |
| 27 | Gemini 2.5 Flash-Lite | 33.7% | — | 26 Sep 2025 | Self-reported | Primary |
| 28 | Llama 4 Scout | 32.8% | — | 05 Apr 2025 | Self-reported | Primary |
