Compare / head-to-head
Gemini 2.5 FlashvsGemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads 2 of 2 shared benchmarks. Gemini 2.5 Flash is 5x cheaper per token. Both offer a 1.0M-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 2
Gemini 3.1 Pro Preview leads
Cheaper per token
Gemini 2.5 Flash
5x cheaper, input + output
Larger context
Tie
both 1.0M tokens
Provider uptime (30d)
100%
Google
Gemini 2.5 Flash
Google · released 2025-06-17
textvisionaudio
Gemini 3.1 Pro Preview
Google · released 2026-02-19
textvisionaudio
Quality
Benchmark matrix
2 shared · 6 only Gemini 2.5 Flash · 7 only Gemini 3.1 Pro Preview| Benchmark | Gemini 2.5 Flash | Gemini 3.1 Pro Preview | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| GPQA Diamond | 82.8% ↗ | 94.3% ↗ | -11.5 pt | Gemini 3.1 Pro Preview |
| LMArena Elo | 1417.3 ↗ | 1480.1 ↗ | -62.8 | Gemini 3.1 Pro Preview |
| Only Gemini 2.5 Flash reports · 6 | ||||
| SWE-bench Verified | 48.9% ↗ | not reported | — | — |
| AIME 2025 | 72% ↗ | not reported | — | — |
| Humanity's Last Exam (no tools) | 11% ↗ | not reported | — | — |
| Aider Polyglot | 56.7% ↗ | not reported | — | — |
| LiveCodeBench | 59.3% ↗ | not reported | — | — |
| MMMU | 79.7% ↗ | not reported | — | — |
| Only Gemini 3.1 Pro Preview reports · 7 | ||||
| AIME 2026 | not reported | 98.3% ↗matharena ⚠ | — | — |
| ARC-AGI-2 | not reported | 77.1% ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 26.8% ↗epoch | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 59.6% ↗epoch | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 95.6% ↗epoch | — | — |
| SimpleQA Verified | not reported | 73.5% ↗epoch | — | — |
| SWE-Bench Pro | not reported | 54.2% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Gemini 2.5 Flash minus Gemini 3.1 Pro Preview in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Gemini 2.5 Flash | Gemini 3.1 Pro Preview | Edge |
|---|---|---|---|
| Context window | 1.0M tokens | 1.0M tokens | Tie |
| Max output | 66K tokens | 66K tokens | Tie |
| Input price / 1M | $0.3 ↗ | $2 ↗ | Gemini 2.5 Flash |
| Output price / 1M | $2.5 ↗ | $12 ↗ | Gemini 2.5 Flash |
| Cached input / 1M | $0.03 ↗ | $0.2 ↗ | Gemini 2.5 Flash |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $2.8 | $14 | Gemini 2.5 Flash |
| Modalities | text · vision · audio | text · vision · audio | Tie |
| Released | 2025-06-17 | 2026-02-19 | — |
| Cited benchmark scores | 9 | 10 | — |
Reliability
Google status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Gemini 2.5 Flash vs …
Models sharing the most benchmarksMore matchups
Gemini 3.1 Pro Preview vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Gemini 2.5 Flash and Gemini 3.1 Pro Preview on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.