Compare / head-to-head
Gemini 3.1 Flash-LitevsGPT-5
GPT-5 leads 3 of 4 shared benchmarks. Gemini 3.1 Flash-Lite is 6.4x cheaper per token. Gemini 3.1 Flash-Lite has the larger context window (1.0M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 3
GPT-5 leads
Cheaper per token
Gemini 3.1 Flash-Lite
6.4x cheaper, input + output
Larger context
Gemini 3.1 Flash-Lite
1.0M tokens
Provider uptime (30d)
100% · 94.2446%
Google · OpenAI
Gemini 3.1 Flash-Lite
Google · released 2026-03-03
textvisionaudio
Quality
Benchmark matrix
4 shared · 5 only Gemini 3.1 Flash-Lite · 4 only GPT-5| Benchmark | Gemini 3.1 Flash-Lite | GPT-5 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| GPQA Diamond | 86.9% ↗ | 86.2% ↗epoch | +0.7 pt | Gemini 3.1 Flash-Lite |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 27.7% ↗epoch | 55.4% ↗epoch | -27.7 pt | GPT-5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 80% ↗epoch | 91.4% ↗epoch | -11.4 pt | GPT-5 |
| SimpleQA Verified | 43.3% ↗ | 50.1% ↗epoch | -6.8 pt | GPT-5 |
| Only Gemini 3.1 Flash-Lite reports · 5 | ||||
| Humanity's Last Exam (no tools) | 16% ↗ | not reported | — | — |
| LiveCodeBench | 72% ↗ | not reported | — | — |
| MMMLU | 88.9% ↗ | not reported | — | — |
| MMMU-Pro | 76.8% ↗ | not reported | — | — |
| MRCR v2 (128k average) | 60.1% ↗ | not reported | — | — |
| Only GPT-5 reports · 4 | ||||
| SWE-bench Verified | not reported | 74.9% ↗ | — | — |
| AIME 2025 | not reported | 94.6% ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 22% ↗epoch | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 73.6% ↗epoch | — | — |
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 3.1 Flash-Lite minus GPT-5 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 3.1 Flash-Lite | GPT-5 | Edge |
|---|---|---|---|
| Context window | 1.0M tokens | 400K tokens | Gemini 3.1 Flash-Lite |
| Max output | 66K tokens | 128K tokens | GPT-5 |
| Input price / 1M | $0.25 ↗ | $1.25 ↗ | Gemini 3.1 Flash-Lite |
| Output price / 1M | $1.5 ↗ | $10 ↗ | Gemini 3.1 Flash-Lite |
| Cached input / 1M | $0.025 ↗ | $0.125 ↗ | Gemini 3.1 Flash-Lite |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.75 | $11.25 | Gemini 3.1 Flash-Lite |
| Modalities | text · vision · audio | text · vision | Gemini 3.1 Flash-Lite |
| Released | 2026-03-03 | 2025-08-07 | — |
| Cited benchmark scores | 10 | 9 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Gemini 3.1 Flash-Lite vs …
Models sharing the most benchmarksMore matchups
GPT-5 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Gemini 3.1 Flash-Lite and GPT-5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.