Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemini 2.5 Pro
65
Winner · 3/8 categoriesGemma 4 26B A4B
64
1/8 categoriesGemini 2.5 Pro· Gemma 4 26B A4B
Pick Gemini 2.5 Pro if you want the stronger benchmark profile. Gemma 4 26B A4B only becomes the better choice if coding is the priority or you want the cheaper token bill.
Gemini 2.5 Pro finishes one point ahead overall, 65 to 64. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
Gemini 2.5 Pro's sharpest advantage is in reasoning, where it averages 61.8 against 44.1. The single biggest benchmark swing on the page is LiveCodeBench, 37% to 77.1%. Gemma 4 26B A4B does hit back in coding, so the answer changes if that is the part of the workload you care about most.
Gemini 2.5 Pro is also the more expensive model on tokens at $1.25 input / $5.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Gemma 4 26B A4B. That is roughly Infinityx on output cost alone. Gemma 4 26B A4B is the reasoning model in the pair, while Gemini 2.5 Pro 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. Gemini 2.5 Pro gives you the larger context window at 1M, compared with 256K for Gemma 4 26B A4B.
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 | Gemini 2.5 Pro | Gemma 4 26B A4B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | 61% | — |
| BrowseComp | 72% | — |
| OSWorld-Verified | 55% | — |
| CodingGemma 4 26B A4B wins | ||
| HumanEval | 75% | — |
| SWE-bench Verified | 63.8% | — |
| LiveCodeBench | 37% | 77.1% |
| SWE-bench Pro | 44% | — |
| Multimodal & GroundedGemini 2.5 Pro wins | ||
| MMMU-Pro | 86% | 73.8% |
| OfficeQA Pro | 84% | — |
| VideoMMMU | 83.6% | — |
| ReasoningGemini 2.5 Pro wins | ||
| MuSR | 79% | — |
| BBH | 81% | 64.8% |
| LongBench v2 | 80% | — |
| MRCRv2 | 83% | 44.1% |
| ARC-AGI-2 | 4.9% | — |
| KnowledgeGemini 2.5 Pro wins | ||
| MMLU | 83% | — |
| GPQA | 83% | 82.3% |
| SuperGPQA | 81% | — |
| MMLU-Pro | 76% | 82.6% |
| HLE | 18.8% | 17.2% |
| FrontierScience | 70% | — |
| SimpleQA | 81% | — |
| HLE w/o tools | — | 8.7% |
| Instruction Following | ||
| Coming soon | ||
| Multilingual | ||
| MGSM | 84% | — |
| MMLU-ProX | 82% | — |
| Mathematics | ||
| AIME 2023 | 84% | — |
| AIME 2024 | 92% | — |
| AIME 2025 | 85% | — |
| HMMT Feb 2023 | 80% | — |
| HMMT Feb 2024 | 82% | — |
| HMMT Feb 2025 | 81% | — |
| BRUMO 2025 | 83% | — |
| MATH-500 | 84% | — |
Gemini 2.5 Pro is ahead overall, 65 to 64. The biggest single separator in this matchup is LiveCodeBench, where the scores are 37% and 77.1%.
Gemini 2.5 Pro has the edge for knowledge tasks in this comparison, averaging 63.9 versus 56.1. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
Gemma 4 26B A4B has the edge for coding in this comparison, averaging 77.1 versus 45.9. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Gemini 2.5 Pro has the edge for reasoning in this comparison, averaging 61.8 versus 44.1. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
Gemini 2.5 Pro has the edge for multimodal and grounded tasks in this comparison, averaging 85.1 versus 73.8. 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.