Model record
Gemini 2.5 Pro model overview
Gemini 2.5 Pro is a api + app model from Google. It was released on March 25, 2025. Its strongest case is native multimodal input, while buyers should account for tiered pricing is workload-dependent.
Gemini 2.5 Pro benchmark snapshot
| Evaluation | Reported score | What it probes |
|---|---|---|
| MMLU-Pro | 86.2 | Broad knowledge and multi-step reasoning |
| GPQA Diamond | 84 | Graduate-level science reasoning |
| SWE-bench Verified | 63.8 | Verified real-repository issue resolution |
| LiveCodeBench | 48.1 | Contamination-aware competitive programming |
| SWE-Bench Pro | Not reported | Longer, harder professional software tasks |
| Artificial Analysis Intelligence Index | Not reported | Composite third-party capability index; version matters |
Scores are percentages reported by model creators or benchmark maintainers under varying settings. A blank is preferable to an inferred result. See our methodology.
Gemini 2.5 Pro strengths
- Native multimodal input
- Strong long-context reasoning
- Good science and code results
Gemini 2.5 Pro limitations
- Tiered pricing is workload-dependent
- Closed weights
Editorial take: Benchmark rank should narrow a shortlist, not close a purchase. Run a private evaluation with representative prompts, failure cases, latency targets, and total token costs.
Compare Gemini 2.5 Pro
- Gemini 2.5 Pro vs Claude 3.7 Sonnet — review fit, trade-offs, listed prices, and an evaluation plan.
- Gemini 2.5 Pro vs GPT-4.1 — review fit, trade-offs, listed prices, and an evaluation plan.
Source record
Specifications and scores are linked to the best source located during review. Provider-reported results are not presented as third-party lab reproductions.
Read Google DeepMind announcement ↗