Benchmark Almanac

Long Code Arena

o1 0.96 leads since December 2024
Not in model cards

Models use project-wide context to generate and complete code, repair builds, find bugs, write commit messages, and summarize modules. Task scores use build success, exact match, API recall, text similarity, localization F1, or a model-based documentation comparison.

This suite uses six different scoring protocols. The displayed aggregate excludes project-level completion and normalizes scores against the participating models. Aggregate values can change with the roster.

Released
June 2024
Kind
Fixing real repositories
Level
University
Scored
Graded by a model
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code, Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
o1 #118 on the capability index
Last model added
December 2024
Scores refreshed
November 18th, 2026

In the authors’ words

Nowadays, the fields of code and natural language processing are evolving rapidly. In particular, models become better at processing long context windows - supported context sizes have increased by orders of magnitude over the last few years. However, there is a shortage of benchmarks for code processing that go beyond a single file of context, while the most popular ones are limited to a single method. With this work, we aim to close this gap by introducing Long Code Arena, a suite of six benchmarks for code processing tasks that require project-wide context. These tasks cover different aspects of code processing: library-based code generation, CI builds repair, project-level code completion, commit message generation, bug localization, and module summarization. For each task, we provide a manually verified dataset for testing, an evaluation suite, and open-source baseline solutions based on popular LLMs to showcase the usage of the dataset and to simplify adoption by other researchers. We publish the benchmark page on HuggingFace Spaces with the leaderboard, links to HuggingFace Hub for all the datasets, and link to the GitHub repository with baselines: https://huggingface.co/spaces/JetBrains-Research/long-code-arena.

Abstract of Long Code Arena: a Set of Benchmarks for Long-Context Code Models (arXiv:2406.11612, CC0)
9
Entries on its own leaderboard, 5 models we track

o1 leads with 0.96 among models released by December 2024 o1 leads with 0.96 among models released by December 2024

Best score per entry from the benchmark's own leaderboard, read on November 18th, 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. This view shows only models we track, each at its best.

The newest model with a score here came out in December 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 o1 0.96
  2. 2 Claude 3.5 Sonnet (snapshot unspecified) 0.84
  3. 3 DeepSeek R1 (snapshot unspecified) 0.80
  4. 4 GPT-4o (snapshot unspecified) 0.70
  5. 5 Gemini 1.5 Pro (snapshot unspecified) 0.58
  6. 6 Llama 3.1-405B 0.47
  7. 7 Claude 3 Haiku 0.42
  8. 8 Llama 3.1-70B 0.29
  9. 9 Llama 3.1-8B 0.12

Source: Official Long Code Arena leaderboard

#EntryScoreSettingDateSource
1 o1 0.96 Dec 2024 Official leaderboard
2 Claude 3.5 Sonnet (snapshot unspecified) 0.84 Official leaderboard
3 DeepSeek R1 (snapshot unspecified) 0.80 Official leaderboard
4 GPT-4o (snapshot unspecified) 0.70 Official leaderboard
5 Gemini 1.5 Pro (snapshot unspecified) 0.58 Official leaderboard
6 Llama 3.1-405B 0.47 Jul 2024 Official leaderboard
7 Claude 3 Haiku 0.42 Mar 2024 Official leaderboard
8 Llama 3.1-70B 0.29 Jul 2024 Official leaderboard
9 Llama 3.1-8B 0.12 Jul 2024 Official leaderboard
#ModelScoreSettingDateSource
1 o1 0.96 Dec 2024 Official leaderboard
2 Llama 3.1-405B 0.47 Jul 2024 Official leaderboard
3 Claude 3 Haiku 0.42 Mar 2024 Official leaderboard
4 Llama 3.1-70B 0.29 Jul 2024 Official leaderboard
5 Llama 3.1-8B 0.12 Jul 2024 Official leaderboard

Rankings by part

We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Bug localization, Module summarization and Library-based code generation. o1 leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

Bug localization

5 models we track have a score here.

  1. 1 o1 0.97
  2. 2 Llama 3.1-405B 0.58
  3. 3 Claude 3 Haiku 0.49
  4. 4 Llama 3.1-70B 0.17
  5. 5 Llama 3.1-8B 0.00

3 models have held number one on the official leaderboard since its release in June 2024

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

Anthropic Meta OpenAI
Own leaderboard Not tested since Dec 2024
o1 0.96

Source: Official Long Code Arena leaderboard

Scores over time

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

Plot with other benchmarks
On the benchmark’s own leaderboard
0.00 0.20 0.40 0.60 0.80 1.00 2024 2025 0.00 0.20 0.40 0.60 0.80 1.00 2024 2025

Source: Official Long Code Arena leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Coding

All 523 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

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 23 months ago, in December 2024, for o1. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (9 entries).
  • Pass Models scored 5 models we track, plus 4 other entries on its leaderboard.
  • Warning Newest score The newest came 23 months ago, in December 2024, for o1.
  • Note Frontier models None of the top 10 has a score. The strongest tested is o1 (#118).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 5 rows for models we track and 4 other entries at the last read.
  • Pass Last read November 18th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check