Codesota · Computer Code · Code Generation · LiveCodeBench ProTasks/Computer Code/Code Generation
Code Generation · benchmark dataset · 2025 · EN

LiveCodeBench Pro.

Elo-rated competitive programming benchmark built from continuously-updated Codeforces, ICPC, and IOI problems. Each LLM is treated as a virtual Codeforces contestant; ratings are fit via Bayesian MAP Elo on the standard Codeforces scale (~800 novice to ~3800 top human). Built by Olympiad medalists to limit contamination.

Paper ↗Download datasetSubmit a result ↵
§ 01 · Leaderboard

Best published scores.

10 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary
elo · higher is better
elo· primary
10 rows
#ModelOrgSubmittedPaper / codeelo
01Gemini 3.1 ProGoogleMay 2026livecodebench-pro-official2887
02Gemini 3 ProAPIGoogleMay 2026livecodebench-pro-official2439
03GPT-5OpenAIApr 2026livecodebench-pro-official2176
04o4-miniOpenAIApr 2026livecodebench-pro-official2092
05Gemini 2.5 ProGoogleApr 2026livecodebench-pro-official1769
06Qwen3-235B-A22BOpenAlibabaApr 2026livecodebench-pro-official1673
07Claude Sonnet 4.5AnthropicApr 2026livecodebench-pro-official1412
08Gemini 2.5 FlashGoogleApr 2026livecodebench-pro-official1288
09DeepSeek R1OpenDeepSeekApr 2026livecodebench-pro-official1161
10o3OpenAIApr 2026livecodebench-pro-official1010
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 03 · Progress

2 steps
of state of the art.

Each row below marks a model that broke the previous record on elo. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

SOTA line · elo
  1. Apr 12, 2026GPT-5OpenAI2176
  2. May 26, 2026Gemini 3.1 ProGoogle2887
Fig 3 · SOTA-setting models only. 2 entries span Apr 2026 → May 2026.
§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies