Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 E2B
~39
0/8 categoriesKimi K2
53
Winner · 2/8 categoriesGemma 4 E2B· Kimi K2
Pick Kimi K2 if you want the stronger benchmark profile. Gemma 4 E2B only becomes the better choice if you want the stronger reasoning-first profile.
Kimi K2 is clearly ahead on the aggregate, 53 to 39. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Kimi K2's sharpest advantage is in coding, where it averages 58.2 against 44. The single biggest benchmark swing on the page is GPQA, 43.4% to 75.1%.
Gemma 4 E2B is the reasoning model in the pair, while Kimi K2 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.
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 | Kimi K2 |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 47.1% |
| BrowseComp | — | 60.2% |
| Tau2-Telecom | — | 66.1% |
| CodingKimi K2 wins | ||
| LiveCodeBench | 44% | 53.7% |
| SWE-bench Verified | — | 65.8% |
| Multimodal & Grounded | ||
| MMMU-Pro | 44.2% | — |
| Reasoning | ||
| BBH | 21.9% | — |
| MRCRv2 | 19.1% | — |
| hle | — | 44.9% |
| KnowledgeKimi K2 wins | ||
| GPQA | 43.4% | 75.1% |
| MMLU-Pro | 60% | 81.1% |
| MMLU | — | 89.5% |
| SuperGPQA | — | 57.2% |
| SimpleQA | — | 31% |
| Instruction Following | ||
| IFEval | — | 89.8% |
| Multilingual | ||
| sweMultilingual | — | 61.1% |
| Mathematics | ||
| AIME 2024 | — | 69.6% |
| AIME 2025 | — | 49.5% |
| MATH-500 | — | 97.4% |
| HMMT Feb 2025 | — | 38.8% |
Kimi K2 is ahead overall, 53 to 39. The biggest single separator in this matchup is GPQA, where the scores are 43.4% and 75.1%.
Kimi K2 has the edge for knowledge tasks in this comparison, averaging 64 versus 54.1. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Kimi K2 has the edge for coding in this comparison, averaging 58.2 versus 44. Inside this category, LiveCodeBench 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.