GameEngineBench
Agents edit C++ files in existing Unreal Engine 5 projects. Runtime tests check the changes, and a model audits whether the behavior meets the specification.
Nitrode ranks nine models in 12 configurations on 110 tasks from nine projects. The paper’s repository link returned 404 on November 20th, 2026.
- Made by
- Nitrode and collaborators
- Released
- July 2026
- Kind
- Building whole projects
- Level
- University
- Scored
- Graded by a model
- Answers
- Agent task
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal, Unreal Engine
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents
- Strongest model tested
- Claude Fable 5 #12 on the capability index
- Last model added
- June 2026
- Scores refreshed
- November 20th, 2026
Claude Fable 5 leads with 55.5% among models released by June 2026 Claude Fable 5 leads with 55.5% 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. 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.
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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 15 more
- 1 Claude Fable 5 max 55.5%
- 2 GPT-5.5 xhigh 29.1%
- 3 Claude Opus 4.8 max 23.6%
- 4
Gemini 3.1 Pro high 18.2%
- 5 Claude Opus 4.7 high 10%
- 6 kimi-for-coding 8.20%
- 7 Claude Sonnet 4.6 high 7.30%
- 8
Qwen3.7-Plus 3.60%
- 9
DeepSeek-V4-Pro 2.70%
Source: Official GameEngineBench leaderboard
- 1 Claude Fable 5 max 55.5%
- 2 GPT-5.5 xhigh 29.1%
- 3 Claude Opus 4.8 max 23.6%
- 4
Gemini 3.1 Pro high 18.2%
- 5 Claude Opus 4.7 high 10%
- 6 Claude Sonnet 4.6 high 7.30%
- 7
Qwen3.7-Plus 3.60%
- 8
DeepSeek-V4-Pro 2.70%
Source: Official GameEngineBench leaderboard
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5 | 55.5% ±4.2 | max | Jun 2026 | Official leaderboard |
| 2 | GPT-5.5 | 29.1% ±3.1 | xhigh | Apr 2026 | Official leaderboard |
| 3 | Claude Opus 4.8 | 23.6% ±2.4 | max | May 2026 | Official leaderboard |
| 4 | | 18.2% ±2.5 | high | Feb 2026 | Official leaderboard |
| 5 | Claude Opus 4.7 | 10% ±1.9 | high | Apr 2026 | Official leaderboard |
| 6 | kimi-for-coding | 8.20% ±1.4 | Official leaderboard | ||
| 7 | Claude Sonnet 4.6 | 7.30% ±1.8 | high | Feb 2026 | Official leaderboard |
| 8 | | 3.60% ±1.1 | Jun 2026 | Official leaderboard | |
| 9 | | 2.70% ±0.9 | Apr 2026 | Official leaderboard |
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5 | 55.5% ±4.2 | max | Jun 2026 | Official leaderboard |
| 2 | GPT-5.5 | 29.1% ±3.1 | xhigh | Apr 2026 | Official leaderboard |
| 3 | Claude Opus 4.8 | 23.6% ±2.4 | max | May 2026 | Official leaderboard |
| 4 | | 18.2% ±2.5 | high | Feb 2026 | Official leaderboard |
| 5 | Claude Opus 4.7 | 10% ±1.9 | high | Apr 2026 | Official leaderboard |
| 6 | Claude Sonnet 4.6 | 7.30% ±1.8 | high | Feb 2026 | Official leaderboard |
| 7 | | 3.60% ±1.1 | Jun 2026 | Official leaderboard | |
| 8 | | 2.70% ±0.9 | Apr 2026 | Official leaderboard |
The best score, 55.5%, costs $18 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official GameEngineBench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5 | max | 55.5% | $18 | ||
| GPT-5.5 | xhigh | 29.1% | $7.80 | ||
| Claude Opus 4.8 | max | 23.6% | $14 | ||
| GPT-5.5 | high | 19.1% | $4.60 | ||
| high | 18.2% | $6.10 | |||
| Claude Opus 4.8 | high | 12.7% | $9.40 | ||
| Claude Opus 4.7 | high | 10% | $8.80 | ||
| GPT-5.5 | medium | 9.10% | $1.90 | ||
| Claude Sonnet 4.6 | high | 7.30% | $5.10 | ||
| 3.60% | $1.20 | ||||
| 2.70% | $0.40 |
The best score, 55.5%, costs $18 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official GameEngineBench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5 | max | 55.5% | $18 | ||
| GPT-5.5 | xhigh | 29.1% | $7.80 | ||
| Claude Opus 4.8 | max | 23.6% | $14 | ||
| GPT-5.5 | high | 19.1% | $4.60 | ||
| high | 18.2% | $6.10 | |||
| Claude Opus 4.8 | high | 12.7% | $9.40 | ||
| Claude Opus 4.7 | high | 10% | $8.80 | ||
| GPT-5.5 | medium | 9.10% | $1.90 | ||
| Claude Sonnet 4.6 | high | 7.30% | $5.10 | ||
| 3.60% | $1.20 | ||||
| 2.70% | $0.40 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official GameEngineBench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official GameEngineBench 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
9 of 10 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 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (9 entries).
- Pass Models scored 8 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 55.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on nitrode.com: 11 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.