Benchmark Almanac

SWE-Pair

DeepSeek V4.1 Flash 90.4% leads since November 2026
Not in model cards

Agents fix two real bugs from the same Python project using one combined issue report. Hidden tests from both pull requests grade each fix.

On November 19, 2026, DeepSeek V4.1 Flash at medium effort led at 90.4% pass@1 across 161 tasks. The board also reports GPT and GLM models.

Made by
Evaligo Labs
Released
November 2026
Kind
Fixing real repositories
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Terminal
Items from
Real work and use
Refresh
One fixed set
Run by
A host
In views
Agents
Strongest model tested
DeepSeek V4.1 Flash #34 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
4
Models scored on its own leaderboard

DeepSeek V4.1 Flash leads with 90.4% among models released by September 2026

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 DeepSeek V4.1 Flash medium 90.4%
  2. 2 GPT-6 Luna max 78.3%
  3. 3 GLM-5.3-Flash medium 66.6%
  4. 4 GPT-5.6 Luna medium 65.4%

Source: Official SWE-Pair leaderboard

#ModelScore ±SettingReleasedRun onSource
1 DeepSeek V4.1 Flash 90.4% ±4.5 medium Sep 2026 Nov 2026 Official leaderboard
2 GPT-6 Luna 78.3% ±6.2 max Sep 2026 Nov 2026 Official leaderboard
3 GLM-5.3-Flash 66.6% ±7.3 medium Aug 2026 Nov 2026 Official leaderboard
4 GPT-5.6 Luna 65.4% ±6.7 medium Jul 2026 Nov 2026 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s own leaderboard: Hard, Public and Private. Each ranks models on one part of the test. DeepSeek V4.1 Flash leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

Hard

3 models we track have a score here.

  1. 1 DeepSeek V4.1 Flash 53.8%
  2. 2 GPT-5.6 Luna ↑2 30.8%
  3. 3 GLM-5.3-Flash 30.8%

Number one over time

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

DeepSeek
Own leaderboard Passed 85% in Nov 2026, by DeepSeek V4.1 Flash

Source: Official SWE-Pair leaderboard

DeepSeek V4.1 Flash on the official leaderboard passed 85% in September 2026

Models released before it came out already scored that high. 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 Best so far
0% 20% 40% 60% 80% 100% Near the ceiling (85%) DeepSeek V4.1 Flash GLM-5.3-Flash GPT-5.6 Luna 0% 20% 40% 60% 80% 100% Near the ceiling (85%) DeepSeek V4.1 Flash GLM-5.3-Flash

Source: Official SWE-Pair 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

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (4 entries).
  • Note Models scored Only 4 models we track.
  • Pass Newest score The newest is from September 2026, for GPT-6 Luna.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is DeepSeek V4.1 Flash (#34).
  • Note Headroom Saturated. The best is 90.4%, past 85% since September 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on labs.evaligo.com: 5 rows for models we track at the last read.
  • Pass Last read November 20th, 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