Benchmark Almanac

DevBench Environment Setup

GPT-4-Turbo-0125 41.7% tops its leaderboard GPT-3.5 Turbo Jan 2024 33.3% leads the models we track
Not in model cards

Models prepare repository environments. The score is the percentage that pass the example usage test.

One track of DevBench. The DevBench record keeps lab scores that combine tracks.

Released
March 2024
Kind
Building whole projects
Level
Expert
Scored
Graded by a model
Answers
Agent task
Tasks
All public
Strongest model tested
GPT-3.5 Turbo Jan 2024 #199 on the capability index
Last model added
January 2024
Scores refreshed
November 12th, 2026
8
Entries on its own leaderboard, 2 models we track

GPT-4-Turbo-0125 tops the leaderboard with 41.7%

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is GPT-3.5 Turbo, at 33.3%.

  1. 41.7 GPT-4-Turbo-0125
  2. 41.7 GPT-4-Turbo-1106
  3. 33.3 GPT-3.5 Turbo
  4. 25.0 CodeLlama-13B-Instruct
  5. 16.7 DeepSeek-Coder-33B-Instruct
  6. 16.7 Code Llama 34B Instruct
  7. 8.30 CodeLlama-7B-Instruct
  8. 8.30 DeepSeek-Coder-1.3B-Instruct
  1. 1 GPT-4-Turbo-0125 41.7%
  2. 2 GPT-4-Turbo-1106 41.7%
  3. 3 GPT-3.5 Turbo Jan 2024 33.3%
  4. 4 CodeLlama-13B-Instruct 25%
  5. 5 DeepSeek-Coder-33B-Instruct 16.7%
  6. 6 Code Llama 34B Instruct 16.7%
  7. 7 CodeLlama-7B-Instruct 8.30%
  8. 8 DeepSeek-Coder-1.3B-Instruct 8.30%

Source: Official DevBench Environment Setup leaderboard

#EntryScoreSettingDateSource
1 GPT-4-Turbo-0125 41.7% Official leaderboard
2 GPT-4-Turbo-1106 41.7% Official leaderboard
3 GPT-3.5 Turbo Jan 2024 33.3% Jan 2024 Official leaderboard
4 CodeLlama-13B-Instruct 25% Official leaderboard
5 DeepSeek-Coder-33B-Instruct 16.7% Official leaderboard
6 Code Llama 34B Instruct 16.7% Aug 2023 Official leaderboard
7 CodeLlama-7B-Instruct 8.30% Official leaderboard
8 DeepSeek-Coder-1.3B-Instruct 8.30% Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) GPT-3.5 Turbo Code Llama 34B Instruct 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) GPT-3.5 Turbo Code Llama 34B Instruct

Source: Official DevBench Environment Setup leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Coding

All 282 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471