Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Claude Sonnet 4.5
68
Winner · 4/8 categoriesGemma 4 E2B
~39
0/8 categoriesClaude Sonnet 4.5· Gemma 4 E2B
Pick Claude Sonnet 4.5 if you want the stronger benchmark profile. Gemma 4 E2B only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.
Claude Sonnet 4.5 is clearly ahead on the aggregate, 68 to 39. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Sonnet 4.5's sharpest advantage is in multimodal & grounded, where it averages 95 against 44.2. The single biggest benchmark swing on the page is MRCRv2, 81% to 19.1%.
Claude Sonnet 4.5 is also the more expensive model on tokens at $3.00 input / $15.00 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. Gemma 4 E2B is the reasoning model in the pair, while Claude Sonnet 4.5 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. Claude Sonnet 4.5 gives you the larger context window at 200K, 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 | Claude Sonnet 4.5 | Gemma 4 E2B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | 50% | — |
| BrowseComp | 74% | — |
| OSWorld-Verified | 61.4% | — |
| VITA-Bench | 17.0% | — |
| CodingClaude Sonnet 4.5 wins | ||
| SWE-bench Verified | 77.2% | — |
| LiveCodeBench | 53% | 44% |
| SWE-bench Pro | 60% | — |
| SWE-Rebench | 60% | — |
| Multimodal & GroundedClaude Sonnet 4.5 wins | ||
| MMMU-Pro | 95% | 44.2% |
| ReasoningClaude Sonnet 4.5 wins | ||
| LongBench v2 | 82% | — |
| MRCRv2 | 81% | 19.1% |
| ARC-AGI-2 | 13.6% | — |
| BBH | — | 21.9% |
| KnowledgeClaude Sonnet 4.5 wins | ||
| MMLU | 95% | — |
| GPQA | 83.4% | 43.4% |
| SuperGPQA | 91% | — |
| MMLU-Pro | 84% | 60% |
| HLE | 21% | — |
| FrontierScience | 84% | — |
| SimpleQA | 91% | — |
| Instruction Following | ||
| IFEval | 90% | — |
| Multilingual | ||
| MGSM | 91% | — |
| MMLU-ProX | 87% | — |
| Mathematics | ||
| AIME 2023 | 97% | — |
| HMMT Feb 2023 | 93% | — |
| HMMT Feb 2024 | 95% | — |
| HMMT Feb 2025 | 94% | — |
| BRUMO 2025 | 96% | — |
| MATH-500 | 88% | — |
Claude Sonnet 4.5 is ahead overall, 68 to 39. The biggest single separator in this matchup is MRCRv2, where the scores are 81% and 19.1%.
Claude Sonnet 4.5 has the edge for knowledge tasks in this comparison, averaging 71.2 versus 54.1. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Claude Sonnet 4.5 has the edge for coding in this comparison, averaging 60.8 versus 44. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Claude Sonnet 4.5 has the edge for reasoning in this comparison, averaging 60.3 versus 19.1. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
Claude Sonnet 4.5 has the edge for multimodal and grounded tasks in this comparison, averaging 95 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.