Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 E4B
~47
0/8 categoriesKimi K2.5
72
Winner · 4/8 categoriesGemma 4 E4B· Kimi K2.5
Pick Kimi K2.5 if you want the stronger benchmark profile. Gemma 4 E4B only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.
Kimi K2.5 is clearly ahead on the aggregate, 72 to 47. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Kimi K2.5's sharpest advantage is in reasoning, where it averages 66.9 against 25.4. The single biggest benchmark swing on the page is BBH, 33.1% to 81%.
Kimi K2.5 is also the more expensive model on tokens at $0.50 input / $2.80 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Gemma 4 E4B. That is roughly Infinityx on output cost alone. Gemma 4 E4B is the reasoning model in the pair, while Kimi K2.5 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 E4B | Kimi K2.5 |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 50.8% |
| BrowseComp | — | 60.6% |
| OSWorld-Verified | — | 63.3% |
| Claw-Eval | — | 52.9% |
| QwenClawBench | — | 54.3% |
| QwenWebBench | — | 1160 |
| TAU3-Bench | — | 65.7% |
| VITA-Bench | — | 36.0% |
| DeepPlanning | — | 14.4% |
| Toolathlon | — | 27.8% |
| MCP Atlas | — | 29.5% |
| MCP-Tasks | — | 59.1% |
| WideResearch | — | 72.7% |
| BrowseComp-VL | — | 42.9% |
| OSWorld | — | 63.3% |
| Tau2-Airline | — | 80.0% |
| Tau2-Telecom | — | 95.9% |
| PinchBench | — | 84.8% |
| BFCL v4 | — | 68.3% |
| AndroidWorld | — | 43.1% |
| WebVoyager | — | 84.3% |
| CodingKimi K2.5 wins | ||
| LiveCodeBench | 52% | 85% |
| HumanEval | — | 99% |
| SWE-bench Verified | — | 76.8% |
| SWE-bench Verified* | — | 70.8% |
| LiveCodeBench v6 | — | 85.6% |
| SWE-bench Pro | — | 53.8% |
| SWE Multilingual | — | 73% |
| SWE-Rebench | — | 58.5% |
| React Native Evals | — | 74.9% |
| NL2Repo | — | 32% |
| Multimodal & GroundedKimi K2.5 wins | ||
| MMMU-Pro | 52.6% | 78.5% |
| MMMU | — | 84.3% |
| OfficeQA Pro | — | 69% |
| RealWorldQA | — | 81.0% |
| OmniDocBench 1.5 | — | 88.8% |
| Video-MME (with subtitle) | — | 87.4% |
| Video-MME (w/o subtitle) | — | 83.2% |
| MathVision | — | 84.2% |
| We-Math | — | 84.7% |
| DynaMath | — | 84.4% |
| MStar | — | 80.5% |
| Design2Code | — | 91.3% |
| Flame-VLM-Code | — | 88.8% |
| Vision2Web | — | 33.2% |
| ImageMining | — | 24.4% |
| MMSearch | — | 58.7% |
| MMSearch-Plus | — | 25.6% |
| SimpleVQA | — | 71.2% |
| ChatCVQA | — | 77.5% |
| MMLongBench-Doc | — | 58.5% |
| CC-OCR | — | 79.7% |
| AI2D_TEST | — | 90.8% |
| CountBench | — | 94.1% |
| RefCOCO (avg) | — | 87.8% |
| VideoMMMU | — | 86.6% |
| MLVU (M-Avg) | — | 85.0% |
| Facts-VLM | — | 57.8% |
| V* | — | 84.3% |
| ReasoningKimi K2.5 wins | ||
| BBH | 33.1% | 81% |
| MRCRv2 | 25.4% | 70% |
| MuSR | — | 72% |
| LongBench v2 | — | 61% |
| AI-Needle | — | 70% |
| KnowledgeKimi K2.5 wins | ||
| GPQA | 58.6% | 87.6% |
| MMLU-Pro | 69.4% | 87.1% |
| MMLU | — | 77% |
| GPQA-D | — | 86.9% |
| SuperGPQA | — | 69.2% |
| MMLU-Pro (Arcee) | — | 87.1% |
| MMLU-Redux | — | 94.5% |
| C-Eval | — | 94% |
| HLE | — | 30.1% |
| FrontierScience | — | 67% |
| SimpleQA | — | 74% |
| Instruction Following | ||
| IFEval | — | 93.9% |
| IFBench | — | 70.2% |
| Multilingual | ||
| MGSM | — | 83% |
| MMLU-ProX | — | 82.3% |
| NOVA-63 | — | 56.0% |
| INCLUDE | — | 83.3% |
| PolyMath | — | 43.1% |
| VWT2k-lite | — | 77.6% |
| MAXIFE | — | 72.8% |
| Mathematics | ||
| AIME 2023 | — | 77% |
| AIME 2024 | — | 79% |
| AIME 2025 | — | 78% |
| AIME26 | — | 95.8% |
| AIME25 (Arcee) | — | 96.3% |
| HMMT Feb 2023 | — | 73% |
| HMMT Feb 2024 | — | 75% |
| HMMT Feb 2025 | — | 74% |
| HMMT Feb 2025 | — | 95.4% |
| HMMT Nov 2025 | — | 91.1% |
| HMMT Feb 2026 | — | 87.1% |
| MMAnswerBench | — | 81.8% |
| BRUMO 2025 | — | 76% |
| MATH-500 | — | 82% |
Kimi K2.5 is ahead overall, 72 to 47. The biggest single separator in this matchup is BBH, where the scores are 33.1% and 81%.
Kimi K2.5 has the edge for knowledge tasks in this comparison, averaging 66.6 versus 65.6. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for coding in this comparison, averaging 66.7 versus 52. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for reasoning in this comparison, averaging 66.9 versus 25.4. Inside this category, BBH is the benchmark that creates the most daylight between them.
Kimi K2.5 has the edge for multimodal and grounded tasks in this comparison, averaging 74.2 versus 52.6. 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.