Benchmark Almanac

Vals Smith: skypilot-org/skypilot

Claude Opus 4.8 30% leads since August 2026
Not in model cards

Agents modify skypilot-org/skypilot to complete software changes from merged pull requests. Hidden tests check the changes and test for regressions.

Vals Smith generates the tasks and publishes model scores for skypilot-org/skypilot in its public repository directory.

Made by
Vals AI
Released
August 2026
Kind
Fixing real repositories
Level
Expert
Scored
Checked automatically
Answers
Agent task
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Code sandbox
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Agents
Strongest model tested
Claude Opus 5 #11 on the capability index
Last model added
July 2026
Scores refreshed
November 21st, 2026
4
Models scored on Vals AI’s leaderboard

3 models share the top score of 30% among models released by July 2026

Best score per model from Vals AI’s leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in July 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 Claude Opus 4.8 30%
  2. 2 GLM-5.2 30%
  3. 3 Claude Opus 5 30%
  4. 4 DeepSeek V4 Flash 0731 26.7%

Source: Vals AI’s leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 4.8 30% Mini-SWE-agent May 2026 Official leaderboard
2 GLM-5.2 30% Mini-SWE-agent Jun 2026 Official leaderboard
3 Claude Opus 5 30% Mini-SWE-agent Jul 2026 Official leaderboard
4 DeepSeek V4 Flash 0731 26.7% Mini-SWE-agent Jul 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
Vals AI leaderboard Not tested since Aug 2026

Source: Vals AI’s 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 Vals AI’s leaderboard
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.8 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.8

Source: Vals AI’s 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 Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 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 July 2026, for DeepSeek V4 Flash 0731.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 5 (#11).
  • Pass Headroom The best is 30%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on Vals AI: 4 rows for models we track at the last read.
  • Pass Last read November 21st, 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