BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases7

GBAEval leaderboard

As of 6 Nov 2026, the top score on GBAEval is 79.6% by Claude Opus 5 (Anthropic), ahead of Claude Fable 5 at 74.5%, across 23 model configurations with a published result (Epoch AI Benchmarking Hub, result dated 24 Jul 2026). The agent plays GBA games from screen and controls, scored on progress. GBAEval is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 6 Nov 2026)

  • Claude Opus 5 holds the top GBAEval score at 79.6% (Epoch AI Benchmarking Hub, 24 Jul 2026).
  • Claude Fable 5 is second on GBAEval at 74.5% (Epoch AI Benchmarking Hub, 9 Jun 2026).
  • GBAEval: Playing Game Boy Advance games as an agent (Epoch AI Benchmarking Hub).
  • 23 model configurations have a published GBAEval result on BenchLeader (BenchLeader, 6 Nov 2026).
  • GBAEval does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Playing Game Boy Advance games as an agent.

Published by
Epoch AI Benchmarking Hub
Category
Agents & tools
Index weight
Reference only
Models
23
Data as of
6 Nov 2026

CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.

What the test looks like

The agent plays GBA games from screen and controls, scored on progress.

How it is scored

Overall score, as published.

What to keep in mind

A games benchmark; small set.

Top 15
  1. 1Claude Opus 579.6%
  2. 2Claude Fable 574.5%
  3. 3Claude Opus 4.870.9%
  4. 4Grok 4.565.4%
  5. 5Claude Sonnet 565.3%
  6. 6GPT-5.553.2%
  7. 7GPT-5.6 Sol52.6%
  8. 8Claude Sonnet 4.648.8%
  9. 9Kimi K348.4%
  10. 10GPT-5.445.1%
  11. 11Claude Opus 4.644.1%
  12. 12Claude Opus 4.743.8%
  13. 13Muse Spark 1.17.9%
  14. 14Gemini 3.5 Flash6.7%
  15. 15Grok Build 0.12.4%
23 of 23
#
1Claude Opus 579.6%65.22026-07-24
2Claude Fable 574.5%66.52026-06-09
3Claude Opus 4.870.9%60.02026-05-28
4Grok 4.565.4%59.82026-07-08
5Claude Sonnet 565.3%55.92026-06-30
6GPT-5.553.2%61.72026-04-23
7GPT-5.6 Sol52.6%55.02026-07-09
8Claude Sonnet 4.648.8%58.22026-02-17
9Kimi K348.4%59.12026-07-16
10GPT-5.445.1%58.02026-03-05
11Claude Opus 4.644.1%62.32026-02-05
12Claude Opus 4.743.8%63.12026-04-16
13Muse Spark 1.17.9%62.22026-07-09
14Gemini 3.5 Flash6.7%48.62026-05-19
15Grok Build 0.12.4%–2026-05-29
16MiniMax M30.9%56.42026-06-01
17Kimi K2.60.9%55.22026-04-20
18Gemini 3.1 Pro0.8%60.52026-02-19
19Kimi K2.7 Code0.8%54.22026-06-12
20Qwen3.7max0.4%60.32026-05-19
21GLM 5.20.0%51.52026-06-16
22MiniMax M2.70.0%56.52026-03-18
23GLM 5.10.0%55.72026-04-07

More agents & tools benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on GBAEval

Cite as: BenchLeader, “GBAEval leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/gbaeval.

GBAEval: questions

What does GBAEval measure?
The agent plays GBA games from screen and controls, scored on progress. Scores are reported in percent of tasks solved; higher is better.
What is the top score on GBAEval?
As of 6 Nov 2026, the highest score on GBAEval is 79.6% by Claude Opus 5 (result dated 24 Jul 2026), ahead of Claude Fable 5 at 74.5%. Scores come from Epoch AI Benchmarking Hub and are re-read daily.
Which AI model leads GBAEval?
Claude Opus 5 leads GBAEval with 79.6% as of 6 Nov 2026 (result dated 24 Jul 2026), ahead of Claude Fable 5 at 74.5%.
How many models have GBAEval results?
23 model configurations have a GBAEval result on BenchLeader, all taken from Epoch AI Benchmarking Hub.
Who runs GBAEval and how often is it updated?
GBAEval is published by Epoch AI Benchmarking Hub. BenchLeader re-reads the published results once a day and records the date each result was published.
Does GBAEval count toward the BenchLeader Index?
No. GBAEval is shown for reference but left out of the composite index.