Exaone 4.0 32B vs GPT-5.1-Codex-Max

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

Exaone 4.0 32B is clearly ahead on the aggregate, 83 to 72. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.1-Codex-Max gives you the larger context window at 400K, compared with 128K for Exaone 4.0 32B.

Quick Verdict

Pick Exaone 4.0 32B if you want the stronger benchmark profile. GPT-5.1-Codex-Max only becomes the better choice if knowledge is the priority or you need the larger 400K context window.

Agentic

Coming soon

Benchmark data for this category is coming soon.

Coding

Coming soon

Benchmark data for this category is coming soon.

Multimodal & Grounded

Coming soon

Benchmark data for this category is coming soon.

Reasoning

Coming soon

Benchmark data for this category is coming soon.

Knowledge

GPT-5.1-Codex-Max

Exaone 4.0 32B

81.8

GPT-5.1-Codex-Max

94

81.8%
MMLU-Pro
Coming soon
Coming soon
SimpleQA
94%

Instruction Following

Coming soon

Benchmark data for this category is coming soon.

Multilingual

Coming soon

Benchmark data for this category is coming soon.

Mathematics

GPT-5.1-Codex-Max

Exaone 4.0 32B

85.3

GPT-5.1-Codex-Max

97.1

85.3%
AIME 2025
98%
Coming soon
AIME 2023
99%
Coming soon
AIME 2024
99%
Coming soon
HMMT Feb 2023
95%
Coming soon
HMMT Feb 2024
97%
Coming soon
HMMT Feb 2025
96%
Coming soon
BRUMO 2025
96%

Frequently Asked Questions

Which is better, Exaone 4.0 32B or GPT-5.1-Codex-Max?

Exaone 4.0 32B is ahead overall, 83 to 72. The biggest single separator in this matchup is AIME 2025, where the scores are 85.3% and 98%.

Which is better for knowledge tasks, Exaone 4.0 32B or GPT-5.1-Codex-Max?

GPT-5.1-Codex-Max has the edge for knowledge tasks in this comparison, averaging 94 versus 81.8. Exaone 4.0 32B stays close enough that the answer can still flip depending on your workload.

Which is better for math, Exaone 4.0 32B or GPT-5.1-Codex-Max?

GPT-5.1-Codex-Max has the edge for math in this comparison, averaging 97.1 versus 85.3. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.

Last updated: March 18, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.