RoboDx
Agents repair faults in robot navigation software. Hidden driving scenarios test the repair. A separate diagnosis track asks models to identify faults without seeing the code.
A Scale AI researcher tested Claude and GPT models on fault diagnosis. On two-fault tasks, some repairs passed every hidden driving check with a fault still present.
- Released
- November 2026
- Kind
- Fixing real repositories
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal, A simulator
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- Claude Opus 5.5 #5 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 100% Claude Opus 5.5 leads with 100%
Best score per entry 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. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
- 1 Claude Opus 5.5 robotics tools 100%
- 2 Claude Sonnet 5.5 robotics tools 99%
- 3 GPT 6.1 robotics tools 98%
- 4 GPT-5.5 robotics tools 93%
- 5 Claude Haiku 5.5 standard tools 71%
Source: The RoboDx paper
Source: The RoboDx paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 100% | robotics tools | Sep 2026 | Official leaderboard |
| 2 | Claude Sonnet 5.5 | 99% | robotics tools | Sep 2026 | Official leaderboard |
| 3 | GPT 6.1 | 98% | robotics tools | Official leaderboard | |
| 4 | GPT-5.5 | 93% | robotics tools | Apr 2026 | Official leaderboard |
| 5 | Claude Haiku 5.5 | 71% | standard tools | Oct 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 100% | robotics tools | Sep 2026 | Official leaderboard |
| 2 | Claude Sonnet 5.5 | 99% | robotics tools | Sep 2026 | Official leaderboard |
| 3 | GPT-5.5 | 93% | robotics tools | Apr 2026 | Official leaderboard |
| 4 | Claude Haiku 5.5 | 71% | standard tools | Oct 2026 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s paper, each ranking models on one part of the test, such as Singles, Pairs and Main run. Claude Opus 5.5 leads 3 of them, and GPT-5.5 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Singles
4 models we track have a score here.
- 1 Claude Opus 5.5 100%
- 2 Claude Sonnet 5.5 100%
- 3 Claude Haiku 5.5 ↑1 97.7%
- 4 GPT-5.5 ↓1 95.5%
Pairs
4 models we track have a score here.
- 1 Claude Opus 5.5 100%
- 2 Claude Sonnet 5.5 98%
- 3 GPT-5.5 90%
- 4 Claude Haiku 5.5 54%
Main run
4 models we track have a score here.
- 1 Claude Opus 5.5 100%
- 2 Claude Sonnet 5.5 99%
- 3 GPT-5.5 93%
- 4 Claude Haiku 5.5 73%
Supplementary pairs
4 models we track have a score here.
- 1 GPT-5.5 ↑2 100%
- 2 Claude Opus 5.5 ↓1 100%
- 3 Claude Sonnet 5.5 ↓1 100%
- 4 Claude Haiku 5.5 50%
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The RoboDx paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5.5 | robotics tools | 100% | |||
| Claude Sonnet 5.5 | robotics tools | 99% | |||
| Claude Opus 5.5 | standard tools | 98% | |||
| Claude Sonnet 5.5 | standard tools | 98% | |||
| GPT-5.5 | robotics tools | 93% | |||
| GPT-5.5 | standard tools | 91% | |||
| Claude Haiku 5.5 | standard tools | 71% | |||
| Claude Haiku 5.5 | robotics tools | 71% |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The RoboDx paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5.5 | robotics tools | 100% | |||
| Claude Sonnet 5.5 | robotics tools | 99% | |||
| Claude Opus 5.5 | standard tools | 98% | |||
| Claude Sonnet 5.5 | standard tools | 98% | |||
| GPT-5.5 | robotics tools | 93% | |||
| GPT-5.5 | standard tools | 91% | |||
| Claude Haiku 5.5 | standard tools | 71% | |||
| Claude Haiku 5.5 | robotics tools | 71% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The RoboDx paper
GPT-5.5 on the official leaderboard passed 85% in April 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.
Source: Official RoboDx 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
- 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 benchmark’s paper (5 entries).
- Pass Models scored 4 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from October 2026, for Claude Haiku 5.5.
- Note Frontier models 2 of the top 10 have a score, which is fine for a retired test. The strongest tested is Claude Opus 5.5 (#5).
- Note Headroom Saturated. The best is 100%, past 85% since April 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 8 rows for models we track and 1 other entry 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.