Benchmark Almanac

ROSTrans

Claude Opus 4.6 10.9% leads since October 2026
Not in model cards

Models migrate robot software from ROS 1 to ROS 2. The evaluator builds each package, runs its nodes, and tests their behavior.

The authors compare six models on 108 tasks.

Released
October 2026
Kind
Fixing real repositories
Level
University
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-5.5 #21 on the capability index
Last model added
April 2026
Scores refreshed
November 20th, 2026
6
Models scored in its paper

Claude Opus 4.6 leads with 10.9% among models released by April 2026

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in April 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 4.6 10.9%
  2. 2 GPT-5.5 10%
  3. 3 Gemini 3.1 Pro 7.20%
  4. 4 Qwen3.5-Plus 6.70%
  5. 5 GLM-5-Turbo 6.50%
  6. 6 DeepSeek-V4-Pro 5.70%

Source: The ROSTrans paper

#ModelScore ±SettingDateSource
1 Claude Opus 4.6 10.9% 5.6 to 16.9 Feb 2026 Official leaderboard
2 GPT-5.5 10% 5.4 to 15.2 Apr 2026 Official leaderboard
3 Gemini 3.1 Pro 7.20% 3.5 to 11.5 Feb 2026 Official leaderboard
4 Qwen3.5-Plus 6.70% 3 to 11.1 Feb 2026 Official leaderboard
5 GLM-5-Turbo 6.50% 2.6 to 10.9 Mar 2026 Official leaderboard
6 DeepSeek-V4-Pro 5.70% 2.2 to 9.8 Apr 2026 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s paper: Interface, Behavior and System. Each ranks models on one part of the test. GPT-5.5 leads 2 of them, and Claude Opus 4.6 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

Interface

6 models we track have a score here.

  1. 1 GPT-5.5 ↑1 9.50%
  2. 2 Claude Opus 4.6 ↓1 8.20%
  3. 3 Qwen3.5-Plus ↑1 6.40%
  4. 4 Gemini 3.1 Pro ↓1 5.50%
  5. 5 DeepSeek-V4-Pro ↑1 4.60%
  6. 6 GLM-5-Turbo ↓1 4.50%

Number one over time

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

Anthropic
Benchmark paper Not tested since Oct 2026

Source: The ROSTrans paper

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
In the benchmark’s paper
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.6 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.6

Source: Official ROSTrans 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for DeepSeek-V4-Pro. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (6 entries).
  • Pass Models scored 6 models we track.
  • Warning Newest score The newest came 7 months ago, in April 2026, for DeepSeek-V4-Pro.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
  • Pass Headroom The best is 10.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 6 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