BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases9

SWE-bench Verified (Epoch)

Epoch AI's own SWE-bench Verified runs with a constant scaffold.

As of 25 Oct 2026, Claude Opus 4.7 leads SWE-bench Verified (Epoch) on BenchLeader with 83.5%, ahead of GPT-5.5 Pre Release at 80.6%, across 33 model configurations with a published result.

Published by
Epoch AI Benchmarking Hub
Category
Coding
Index weight
0.5
Models
33
Data as of
25 Oct 2026
Newest result
16 Jun 2026

The publisher has posted no new results on this board since 16 Jun 2026. BenchLeader re-reads it every day, so newer models appear here as soon as they are published.

CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.

What the test looks like

SWE-bench Verified is 500 real GitHub issues from popular Python repositories, each screened by human annotators to make sure the task is well specified and the tests are fair. The model reads the issue, edits the repository, and its patch is accepted only if the hidden tests pass.

How it is scored

Percent of the 500 issues resolved, run by Epoch AI.

What to keep in mind

Epoch AI's own SWE-bench Verified runs, with one constant scaffold across every model. A fixed scaffold makes models comparable but can understate those tuned for a different agent loop. Numbers are usually below the labs' own best reports. See also the SWE-bench Verified (bash only) board.

Top 15
  1. 1Claude Opus 4.7 (max)83.5%
  2. 2GPT-5.5 Pre Release (xhigh)80.6%
  3. 3Gemini 3.5 Flash (high)79.3%
  4. 4Claude Opus 4.678.7%
  5. 5GLM 5.2 (max)78.7%
  6. 6DeepSeek V4 Pro (max)77.6%
  7. 7Qwen3.7 (max)77.3%
  8. 8GPT-5.4 (high)76.9%
  9. 9Qwen3.6 Max (max)76.7%
  10. 10Claude Opus 4.576.7%
  11. 11Kimi K2.676.7%
  12. 12Gemini 3.1 Pro Customtools75.6%
  13. 13Gemini 3 Flash75.4%
  14. 14Claude Sonnet 4.675.2%
  15. 15GPT-5.3-Codex (high)74.8%
33 of 33
#
1Claude Opus 4.7max83.5%62.42026-04-16
2GPT-5.5 Pre Releasexhigh80.6%–2026-04-23
3Gemini 3.5 Flashhigh79.3%63.12026-05-19
4Claude Opus 4.678.7%62.52026-02-05
5GLM 5.2max78.7%62.32026-06-16
6DeepSeek V4 Promax77.6%60.82026-04-24
7Qwen3.7max77.3%60.62026-05-19
8GPT-5.4high76.9%58.92026-03-05
9Qwen3.6 Maxmax76.7%62.32026-04-20
10Claude Opus 4.576.7%57.92025-11-24
11Kimi K2.676.7%55.32026-04-20
12Gemini 3.1 Pro Customtools75.6%–2026-02-19
13Gemini 3 Flash75.4%57.02025-12-17
14Claude Sonnet 4.675.2%57.12026-02-17
15GPT-5.3-Codexhigh74.8%–2026-02-05
16GLM 5.174.2%55.92026-04-07
17GPT-5.2high73.8%56.02025-12-11
18Kimi K2.573.8%54.52026-01-27
19GPT-5high73.5%57.92025-08-07
20Claude Opus 4.173.3%51.52025-08-05
21Gemini 3 Pro72.9%60.42025-11-18
22GLM-572.1%54.92026-02-11
23GPT-5medium71.5%57.52025-08-07
24Claude Sonnet 4.571.3%53.72025-09-29
25Claude Opus 470.7%52.62025-05-22
26GPT-5.1high68.0%57.72025-11-13
27GPT-5 minimedium64.7%53.82025-08-07
28o3medium62.3%53.32025-04-16
29Claude 3.7 Sonnet61.0%50.02025-02-24
30Qwen3.6 Plus57.9%58.82026-03-31
31Gemini 2.5 Pro57.6%53.92025-06-17
32GPT-4.148.5%48.32025-04-14
33GPT-4o31.0%43.92024-11-20

More coding benchmarks · All LLM benchmarks

Cite as: BenchLeader, “SWE-bench Verified (Epoch) leaderboard”, data as of 25 Oct 2026, https://www.benchleader.com/benchmarks/swe_bench_verified_epoch.

SWE-bench Verified (Epoch): questions

What does SWE-bench Verified (Epoch) measure?
SWE-bench Verified is 500 real GitHub issues from popular Python repositories, each screened by human annotators to make sure the task is well specified and the tests are fair. The model reads the issue, edits the repository, and its patch is accepted only if the hidden tests pass. Scores are reported in percent of tasks solved; higher is better.
Which AI model leads SWE-bench Verified (Epoch)?
Claude Opus 4.7 leads SWE-bench Verified (Epoch) with 83.5% as of 25 Oct 2026, ahead of GPT-5.5 Pre Release at 80.6%.
How many models have SWE-bench Verified (Epoch) results?
33 model configurations have a SWE-bench Verified (Epoch) result on BenchLeader, all taken from Epoch AI Benchmarking Hub.
Who runs SWE-bench Verified (Epoch) and how often is it updated?
SWE-bench Verified (Epoch) is published by Epoch AI Benchmarking Hub. BenchLeader re-reads the published results once a day and records the date each result was published.
Does SWE-bench Verified (Epoch) count toward the BenchLeader Index?
Yes. SWE-bench Verified (Epoch) contributes to the coding category of the BenchLeader Index, normalised so that 50 is the average of the evaluated models.