Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 E2B
~39
0/8 categoriesGPT-5.1-Codex-Max
81
Winner · 4/8 categoriesGemma 4 E2B· GPT-5.1-Codex-Max
Pick GPT-5.1-Codex-Max if you want the stronger benchmark profile. Gemma 4 E2B only becomes the better choice if you want the cheaper token bill.
GPT-5.1-Codex-Max is clearly ahead on the aggregate, 81 to 39. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.1-Codex-Max's sharpest advantage is in reasoning, where it averages 91.5 against 19.1. The single biggest benchmark swing on the page is MRCRv2, 19.1% to 93%.
GPT-5.1-Codex-Max is also the more expensive model on tokens at $2.00 input / $8.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Gemma 4 E2B. That is roughly Infinityx on output cost alone. GPT-5.1-Codex-Max gives you the larger context window at 400K, compared with 128K for Gemma 4 E2B.
BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.
Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.
| Benchmark | Gemma 4 E2B | GPT-5.1-Codex-Max |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 90% |
| BrowseComp | — | 85% |
| OSWorld-Verified | — | 82% |
| CodingGPT-5.1-Codex-Max wins | ||
| LiveCodeBench | 44% | 67% |
| HumanEval | — | 94% |
| SWE-bench Verified | — | 77.9% |
| SWE-bench Pro | — | 84% |
| Multimodal & GroundedGPT-5.1-Codex-Max wins | ||
| MMMU-Pro | 44.2% | 85% |
| OfficeQA Pro | — | 92% |
| ReasoningGPT-5.1-Codex-Max wins | ||
| BBH | 21.9% | 92% |
| MRCRv2 | 19.1% | 93% |
| MuSR | — | 92% |
| LongBench v2 | — | 90% |
| KnowledgeGPT-5.1-Codex-Max wins | ||
| GPQA | 43.4% | 96% |
| MMLU-Pro | 60% | 82% |
| MMLU | — | 98% |
| SuperGPQA | — | 94% |
| HLE | — | 27% |
| FrontierScience | — | 84% |
| SimpleQA | — | 94% |
| Instruction Following | ||
| IFEval | — | 91% |
| Multilingual | ||
| MGSM | — | 89% |
| MMLU-ProX | — | 87% |
| Mathematics | ||
| AIME 2023 | — | 99% |
| AIME 2024 | — | 99% |
| AIME 2025 | — | 98% |
| HMMT Feb 2023 | — | 95% |
| HMMT Feb 2024 | — | 97% |
| HMMT Feb 2025 | — | 96% |
| BRUMO 2025 | — | 96% |
| MATH-500 | — | 93% |
GPT-5.1-Codex-Max is ahead overall, 81 to 39. The biggest single separator in this matchup is MRCRv2, where the scores are 19.1% and 93%.
GPT-5.1-Codex-Max has the edge for knowledge tasks in this comparison, averaging 74.4 versus 54.1. Inside this category, GPQA is the benchmark that creates the most daylight between them.
GPT-5.1-Codex-Max has the edge for coding in this comparison, averaging 76.1 versus 44. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
GPT-5.1-Codex-Max has the edge for reasoning in this comparison, averaging 91.5 versus 19.1. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
GPT-5.1-Codex-Max has the edge for multimodal and grounded tasks in this comparison, averaging 88.2 versus 44.2. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
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.