Benchmark Almanac

SWE-Clar

GPT-6 Astra 67% leads since October 2026
Not in model cards

Agents question a simulated client about an incomplete request, then build greenfield software from real Upwork jobs. Acceptance tests score the build.

100 tasks from jobs that each paid at least US$4,000. A separate run scores the agent's answers about client requirements. 9 models at release.

Made by
Upwork
Released
October 2026
Kind
Building whole projects
Level
Expert
Scored
Checked automatically
Answers
Code
Tasks
All public
Strongest model tested
GPT-6 Astra #3 on the capability index
Last model added
September 2026
Scores refreshed
November 12th, 2026
9
Models scored on its own leaderboard

GPT-6 Astra leads with 67% among models released by September 2026

Best score per model from the benchmark's own leaderboard, read on November 12th, 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. 67.0 GPT-6 Astra
  2. 63.0 Claude Opus 5
  3. 60.0 Claude Fable 5.1
  4. 57.0 GPT-5.6 Sol
  5. 55.0 Qwen 3.8 Max
  6. 54.0 GLM-5.3
  7. 49.0 GPT-5.6 Luna
  8. 49.0 Kimi K3
  9. 39.0 GLM-5.3-Flash
  1. 1 GPT-6 Astra 67%
  2. 2 Claude Opus 5 63%
  3. 3 Claude Fable 5.1 60%
  4. 4 GPT-5.6 Sol 57%
  5. 5 Qwen 3.8 Max 55%
  6. 6 GLM-5.3 54%
  7. 7 GPT-5.6 Luna 49%
  8. 8 Kimi K3 49%
  9. 9 GLM-5.3-Flash 39%

Source: Official SWE-Clar leaderboard

#ModelScoreSettingDateSource
1 GPT-6 Astra 67% SWE-Clar clarify Sep 2026 Official leaderboard
2 Claude Opus 5 63% SWE-Clar clarify Jul 2026 Official leaderboard
3 Claude Fable 5.1 60% SWE-Clar clarify Sep 2026 Official leaderboard
4 GPT-5.6 Sol 57% SWE-Clar clarify Jul 2026 Official leaderboard
5 Qwen 3.8 Max 55% SWE-Clar clarify Aug 2026 Official leaderboard
6 GLM-5.3 54% SWE-Clar clarify Aug 2026 Official leaderboard
7 GPT-5.6 Luna 49% SWE-Clar clarify Jul 2026 Official leaderboard
8 Kimi K3 49% SWE-Clar clarify Jul 2026 Official leaderboard
9 GLM-5.3-Flash 39% SWE-Clar clarify Aug 2026 Official leaderboard

Number one over time

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

OpenAI
Own leaderboard 1 leader
GPT-6 Astra 67%

Source: Official SWE-Clar 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% Near the ceiling (85%) GPT-6 Astra Claude Opus 5 GPT-5.6 Sol 0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-6 Astra GPT-5.6 Sol

Source: Official SWE-Clar 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