Benchmark Almanac

ReviewBench

Claude Opus 5.5 73.3% leads since Oct 2026 Not in model cards

AI code review systems review 219 real pull requests from 187 repositories in 19 languages. A judge scores found issues against a multi-source golden set for precision, recall and F1.

Research preview released 2026-10-05. Senior engineers agreed with the ground truth 96.6% of the time. Harbor hosts it as review-bench/reviewbench-public.

Made by GitHub and Microsoft Released Oct 2026 Fixing real repositories All tasks public Last model added Sep 2026 Scores refreshed 2 Nov 2026
Level
Expert Specialists with years of training, often over hours of work
Scored
Graded by a model A language model scores each response, usually against a rubric.
Answers
Agent task Many steps in a terminal, browser, desktop, app, game or robot.
review-bench/ReviewBench 88 stars Leaderboard github.blog
5
Entries on its own leaderboard, 4 models we track

Claude Opus 5.5 leads with 73.3%

Best score per entry from the benchmark's own leaderboard, read on 2 Nov 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.

  1. 73.3 Claude Opus 5.5
  2. 70.2 GPT-5.6 Sol
  3. 64.8 deepseek-flash
  4. 64.0 DeepSeek-V4-Flash
  5. 63.1 Claude Sonnet 5.5
  1. 1 Claude Opus 5.5 73.3%
  2. 2 GPT-5.6 Sol max 70.2%
  3. 3 deepseek-flash high 64.8%
  4. 4 DeepSeek-V4-Flash 64%
  5. 5 Claude Sonnet 5.5 63.1%
#EntryScoreSettingDateSource
1 Claude Opus 5.5 73.3% Laude RevEngine Sep 2026 Official leaderboard
2 GPT-5.6 Sol 70.2% max, Codex Jul 2026 Official leaderboard
3 deepseek-flash 64.8% high, DeepSeek Harness Reviewer Oct 2026 Official leaderboard
4 DeepSeek-V4-Flash 64% opswiki Apr 2026 Official leaderboard
5 Claude Sonnet 5.5 63.1% Klaussy Sep 2026 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic
Own leaderboard 1 leader
Claude Opus 5.5 73.3%

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% 2026 Near the ceiling (85%) Claude Opus 5.5 GPT-5.6 Sol DeepSeek-V4-Flash 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 5.5 DeepSeek-V4-Flash

No lab model card reports it yet

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.

More in Coding

All 243 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%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Opus 5.5 93.9%
  • 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%
  • 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