Benchmark Almanac

OpenGameEval

Gemini 3.1 Pro 55.3% leads since February 2026
Not in model cards
Version 47-eval set

Agents write Luau scripts and edit objects in Roblox Studio. The original suite checks 47 changes to game mechanics and scenes.

Roblox archives results for 24 models on the original 47 tasks. Its release log dates the first batch to October 2025.

Made by
Roblox
Released
October 2025
Kind
Building whole projects
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Roblox Studio
Items from
Written by experts
Run by
Anyone
In views
Agents
Strongest model tested
GPT-5.4 #28 on the capability index
Last model added
April 2026
Scores refreshed
November 20th, 2026
24
Entries on its own leaderboard, 22 models we track

Gemini 3.1 Pro leads with 55.3% among models released by April 2026 Gemini 3.1 Pro leads with 55.3% among models released by April 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 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 Gemini 3.1 Pro 55.3%
  2. 2 Gemini 3 Flash 54.7%
  3. 3 Claude Opus 4.6 51.9%
  4. 4 GLM-5 51.7%
  5. 5 Gemini 3 Pro 48.9%
  6. 6 Claude Sonnet 4.6 46.4%
  7. 7 Claude Opus 4.7 46.4%
  8. 8 Kimi K2.5 thinking 45.7%
  9. 9 Claude Opus 4.5 44.5%
  10. 10 GLM-4.7 43.8%
  11. 11 GPT Codex 5.3 40.4%
  12. 12 GLM-4.5 40.4%
  13. 13 Gemini 2.5 Pro Jun 2025 38.5%
  14. 14 Claude Sonnet 4.5 38.5%
  15. 15 GLM-4.6 38.5%
  16. 16 LIMI GLM 4.5 38.1%
  17. 17 Claude Haiku 4.5 35.7%
  18. 18 GPT-5.4 reasoning: m 35.1%
  19. 19 Kimi K2 Thinking 33.2%
  20. 20 GPT-5.1 31.1%
  21. 21 GPT-5.2 30.6%
  22. 22 gpt-oss-120b 29.8%
  23. 23 MiniMax-M2 24.7%
  24. 24 Gemini 2.5 Flash Sep 2025 23.4%

Source: Official OpenGameEval leaderboard

#EntryScoreSettingDateSource
1 Gemini 3.1 Pro 55.3% Roblox Studio Assistant Feb 2026 Official leaderboard
2 Gemini 3 Flash 54.7% Roblox Studio Assistant Dec 2025 Official leaderboard
3 Claude Opus 4.6 51.9% Roblox Studio Assistant Feb 2026 Official leaderboard
4 GLM-5 51.7% Roblox Studio Assistant Feb 2026 Official leaderboard
5 Gemini 3 Pro 48.9% Roblox Studio Assistant Nov 2025 Official leaderboard
6 Claude Sonnet 4.6 46.4% Roblox Studio Assistant Feb 2026 Official leaderboard
7 Claude Opus 4.7 46.4% Roblox Studio Assistant Apr 2026 Official leaderboard
8 Kimi K2.5 45.7% thinking, Roblox Studio Assistant Jan 2026 Official leaderboard
9 Claude Opus 4.5 44.5% Roblox Studio Assistant Nov 2025 Official leaderboard
10 GLM-4.7 43.8% Roblox Studio Assistant Dec 2025 Official leaderboard
11 GPT Codex 5.3 40.4% Roblox Studio Assistant Official leaderboard
12 GLM-4.5 40.4% Roblox Studio Assistant Aug 2025 Official leaderboard
13 Gemini 2.5 Pro Jun 2025 38.5% Roblox Studio Assistant Jun 2025 Official leaderboard
14 Claude Sonnet 4.5 38.5% Roblox Studio Assistant Sep 2025 Official leaderboard
15 GLM-4.6 38.5% Roblox Studio Assistant Sep 2025 Official leaderboard
16 LIMI GLM 4.5 38.1% Roblox Studio Assistant Official leaderboard
17 Claude Haiku 4.5 35.7% Roblox Studio Assistant Oct 2025 Official leaderboard
18 GPT-5.4 35.1% reasoning: m, Roblox Studio Assistant Mar 2026 Official leaderboard
19 Kimi K2 Thinking 33.2% Roblox Studio Assistant Nov 2025 Official leaderboard
20 GPT-5.1 31.1% Roblox Studio Assistant Nov 2025 Official leaderboard
21 GPT-5.2 30.6% Roblox Studio Assistant Dec 2025 Official leaderboard
22 gpt-oss-120b 29.8% Roblox Studio Assistant Aug 2025 Official leaderboard
23 MiniMax-M2 24.7% Roblox Studio Assistant Oct 2025 Official leaderboard
24 Gemini 2.5 Flash Sep 2025 23.4% Roblox Studio Assistant Sep 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 3.1 Pro 55.3% Roblox Studio Assistant Feb 2026 Official leaderboard
2 Gemini 3 Flash 54.7% Roblox Studio Assistant Dec 2025 Official leaderboard
3 Claude Opus 4.6 51.9% Roblox Studio Assistant Feb 2026 Official leaderboard
4 GLM-5 51.7% Roblox Studio Assistant Feb 2026 Official leaderboard
5 Gemini 3 Pro 48.9% Roblox Studio Assistant Nov 2025 Official leaderboard
6 Claude Sonnet 4.6 46.4% Roblox Studio Assistant Feb 2026 Official leaderboard
7 Claude Opus 4.7 46.4% Roblox Studio Assistant Apr 2026 Official leaderboard
8 Kimi K2.5 45.7% thinking, Roblox Studio Assistant Jan 2026 Official leaderboard
9 Claude Opus 4.5 44.5% Roblox Studio Assistant Nov 2025 Official leaderboard
10 GLM-4.7 43.8% Roblox Studio Assistant Dec 2025 Official leaderboard
11 GLM-4.5 40.4% Roblox Studio Assistant Aug 2025 Official leaderboard
12 Gemini 2.5 Pro Jun 2025 38.5% Roblox Studio Assistant Jun 2025 Official leaderboard
13 Claude Sonnet 4.5 38.5% Roblox Studio Assistant Sep 2025 Official leaderboard
14 GLM-4.6 38.5% Roblox Studio Assistant Sep 2025 Official leaderboard
15 Claude Haiku 4.5 35.7% Roblox Studio Assistant Oct 2025 Official leaderboard
16 GPT-5.4 35.1% reasoning: m, Roblox Studio Assistant Mar 2026 Official leaderboard
17 Kimi K2 Thinking 33.2% Roblox Studio Assistant Nov 2025 Official leaderboard
18 GPT-5.1 31.1% Roblox Studio Assistant Nov 2025 Official leaderboard
19 GPT-5.2 30.6% Roblox Studio Assistant Dec 2025 Official leaderboard
20 gpt-oss-120b 29.8% Roblox Studio Assistant Aug 2025 Official leaderboard
21 MiniMax-M2 24.7% Roblox Studio Assistant Oct 2025 Official leaderboard
22 Gemini 2.5 Flash Sep 2025 23.4% Roblox Studio Assistant Sep 2025 Official leaderboard

4 models have held number one on the official leaderboard since its release in October 2025

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

Z.ai Google DeepMind
Own leaderboard Replaced by Expanded Eval Set, Apr 2026

Source: Official OpenGameEval 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% 2025 2026 Near the ceiling (85%) Gemini 3.1 Pro Gemini 3 Pro GLM-4.5 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Gemini 3.1 Pro Gemini 3 Pro

Source: Official OpenGameEval 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.

Versions

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

Z.ai Google DeepMind Anthropic
OpenGameEval Expanded Eval Set Not tested since Jun 2026
OpenGameEval Replaced by Expanded Eval Set, Apr 2026
OpenGameEval Expanded Eval Set Not tested since Jun 2026

Source: Official leaderboards

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 (24 entries).
  • Pass Models scored 22 models we track, plus 2 other entries on its leaderboard.
  • Note Newest score The newest came 7 months ago, in April 2026, for Claude Opus 4.7. That’s expected for a test replaced by OpenGameEval Expanded Eval Set.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.4 (#28).
  • Pass Headroom The best is 55.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 22 rows for models we track and 2 other entries 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