Benchmark Almanac

OpenGameEval Debug Evals

Claude Fable 5 64.7% leads since June 2026
Not in model cards

Agents diagnose and fix faults in Roblox Studio games. The authors created 30 debugging tasks from 15 scenarios.

Roblox ranks 11 models on debugging. Its October paper reports a separate 29-task comparison after the authors withdrew one faulty task.

Made by
Roblox
Released
March 2026
Kind
Fixing real repositories
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Actions, Code
Interaction
Agentic
Environment
Roblox Studio
Items from
Written by experts
Refresh
One fixed set
Run by
Anyone
In views
Agents
Strongest model tested
Claude Fable 5 #12 on the capability index
Last model added
June 2026
Scores refreshed
November 20th, 2026
11
Entries on its own leaderboard, 10 models we track

Claude Fable 5 leads with 64.7% among models released by June 2026 Claude Fable 5 leads with 64.7% among models released by June 2026

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

The newest model with a score here came out in June 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 Fable 5 64.7%
  2. 2 Gemini 3.1 Pro 56.7%
  3. 3 GLM-5 56%
  4. 4 Claude Opus 4.7 52.7%
  5. 5 Gemini 3 Flash 51.3%
  6. 6 GPT-5.4 Reasoning: M 51.3%
  7. 7 Claude Opus 4.6 50.7%
  8. 8 GPT-5.5 Reasoning: M 50%
  9. 9 Gemini 3.5 Flash 49.3%
  10. 10 GPT Codex 5.3 47.3%
  11. 11 Claude Sonnet 4.6 46%

Source: Official OpenGameEval Debug Evals leaderboard

#EntryScoreSettingDateSource
1 Claude Fable 5 64.7% Roblox Studio Assistant Jun 2026 Official leaderboard
2 Gemini 3.1 Pro 56.7% Roblox Studio Assistant Feb 2026 Official leaderboard
3 GLM-5 56% Roblox Studio Assistant Feb 2026 Official leaderboard
4 Claude Opus 4.7 52.7% Roblox Studio Assistant Apr 2026 Official leaderboard
5 Gemini 3 Flash 51.3% Roblox Studio Assistant Dec 2025 Official leaderboard
6 GPT-5.4 51.3% Reasoning: M, Roblox Studio Assistant Mar 2026 Official leaderboard
7 Claude Opus 4.6 50.7% Roblox Studio Assistant Feb 2026 Official leaderboard
8 GPT-5.5 50% Reasoning: M, Roblox Studio Assistant Apr 2026 Official leaderboard
9 Gemini 3.5 Flash 49.3% Roblox Studio Assistant May 2026 Official leaderboard
10 GPT Codex 5.3 47.3% Roblox Studio Assistant Official leaderboard
11 Claude Sonnet 4.6 46% Roblox Studio Assistant Feb 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5 64.7% Roblox Studio Assistant Jun 2026 Official leaderboard
2 Gemini 3.1 Pro 56.7% Roblox Studio Assistant Feb 2026 Official leaderboard
3 GLM-5 56% Roblox Studio Assistant Feb 2026 Official leaderboard
4 Claude Opus 4.7 52.7% Roblox Studio Assistant Apr 2026 Official leaderboard
5 Gemini 3 Flash 51.3% Roblox Studio Assistant Dec 2025 Official leaderboard
6 GPT-5.4 51.3% Reasoning: M, Roblox Studio Assistant Mar 2026 Official leaderboard
7 Claude Opus 4.6 50.7% Roblox Studio Assistant Feb 2026 Official leaderboard
8 GPT-5.5 50% Reasoning: M, Roblox Studio Assistant Apr 2026 Official leaderboard
9 Gemini 3.5 Flash 49.3% Roblox Studio Assistant May 2026 Official leaderboard
10 Claude Sonnet 4.6 46% Roblox Studio Assistant Feb 2026 Official leaderboard

2 models have held number one on the official leaderboard since its release in March 2026

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

Google DeepMind Anthropic
Own leaderboard Not tested since Jun 2026

Source: Official OpenGameEval Debug Evals 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 the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Fable 5 Gemini 3.1 Pro Gemini 3 Flash 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Fable 5 Gemini 3.1 Pro

Source: Official OpenGameEval Debug Evals 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 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (11 entries).
  • Pass Models scored 10 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from June 2026, for Claude Fable 5.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Fable 5 (#12).
  • Pass Headroom The best is 64.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 10 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.

How we check