Benchmark Almanac

3D GameDev Arena

Claude Opus 5 99.8% leads since November 2026
Not in model cards

Agents build playable 3D browser games from specifications and reference images. Players compare anonymous game pairs. The authors also test functionality and playability.

The paper compares four configurations on a benchmark of 108 tasks across 14 genres. The live arena also publishes generation success rates.

Released
November 2026
Kind
Building whole projects
Level
Expert
Scored
Ranked by votes
Answers
Agent task
Tasks
All public
Measures
Preference
Language
English
In and out
Text, Images → Code, Actions
Interaction
Agentic
Environment
Browser
Items from
Live play or votes
Refresh
Live
Run by
A host
In views
Agents, Vision, Kept fresh
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
10
Entries on its own leaderboard, 9 models we track

Claude Opus 5 leads with 99.8% among models released by September 2026 Claude Opus 5 leads with 99.8% among models released by September 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 September 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 5 99.8%
  2. 2 Claude Sonnet 5 89.9%
  3. 3 GPT-6 Astra ultra 68.6%
  4. 4 GPT-6.1 Sol ultra 63.9%
  5. 5 GPT-6 Sol ultra 61.3%
  6. 6 GPT-5.6 Sol ultra 48.1%
  7. 7 GLM-5.3 max 31.1%
  8. 8 Kimi K3 max 28.6%
  9. 9 Grok 4.7 xhigh 26.7%
  10. 10 Qwen 3.8 max 18.9%

Source: Official 3D GameDev Arena leaderboard

#EntryScore ±SettingDateSource
1 Claude Opus 5 99.8% 99.5 to 100 Claude Code Jul 2026 Official leaderboard
2 Claude Sonnet 5 89.9% ±0.2 Claude Code Jun 2026 Official leaderboard
3 GPT-6 Astra 68.6% ±8.2 ultra, Codex Sep 2026 Official leaderboard
4 GPT-6.1 Sol 63.9% ±6.4 ultra, Codex Sep 2026 Official leaderboard
5 GPT-6 Sol 61.3% ±17.9 ultra, Codex Sep 2026 Official leaderboard
6 GPT-5.6 Sol 48.1% ±7.6 ultra, Codex Jul 2026 Official leaderboard
7 GLM-5.3 31.1% ±14.1 max, ZCode Aug 2026 Official leaderboard
8 Kimi K3 28.6% ±7.1 max, Kimi Code Jul 2026 Official leaderboard
9 Grok 4.7 26.7% ±12.5 xhigh, GrokBuild Sep 2026 Official leaderboard
10 Qwen 3.8 18.9% ±8.2 max, Pi Official leaderboard
#ModelScore ±SettingDateSource
1 Claude Opus 5 99.8% 99.5 to 100 Claude Code Jul 2026 Official leaderboard
2 Claude Sonnet 5 89.9% ±0.2 Claude Code Jun 2026 Official leaderboard
3 GPT-6 Astra 68.6% ±8.2 ultra, Codex Sep 2026 Official leaderboard
4 GPT-6.1 Sol 63.9% ±6.4 ultra, Codex Sep 2026 Official leaderboard
5 GPT-6 Sol 61.3% ±17.9 ultra, Codex Sep 2026 Official leaderboard
6 GPT-5.6 Sol 48.1% ±7.6 ultra, Codex Jul 2026 Official leaderboard
7 GLM-5.3 31.1% ±14.1 max, ZCode Aug 2026 Official leaderboard
8 Kimi K3 28.6% ±7.1 max, Kimi Code Jul 2026 Official leaderboard
9 Grok 4.7 26.7% ±12.5 xhigh, GrokBuild Sep 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
Own leaderboard Passed 85% in Nov 2026, by Claude Opus 5

Source: Official 3D GameDev Arena leaderboard

Claude Sonnet 5 on the official leaderboard passed 85% in June 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.

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 Opus 5 Claude Sonnet 5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 5 Claude Sonnet 5

Source: Official 3D GameDev Arena 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 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 9 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
  • Note Frontier models 2 of the top 10 have a score, which is fine for a retired test. The strongest tested is GPT-6 Astra (#4).
  • Note Headroom Saturated. The best is 99.8%, past 85% since June 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on 110.238.108.113: 9 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