Compare / head-to-head
Gemini 3.1 Flash-LitevsPhi-4
Gemini 3.1 Flash-Lite leads 2 of 2 shared benchmarks. 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
2 – 0
Gemini 3.1 Flash-Lite leads
Cheaper per token
—
list price, input + output
Larger context
Gemini 3.1 Flash-Lite
1.0M tokens
Provider uptime (30d)
100% · —
Google · Microsoft
Gemini 3.1 Flash-Lite
Google · released 2026-03-03
textvisionaudio
Phi-4
Microsoft · released 2024-12-12
text
- Context
- 16K
- Max out
- 16K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 11 · 7 core
Quality
Benchmark matrix
2 shared · 7 only Gemini 3.1 Flash-Lite · 8 only Phi-4| Benchmark | Gemini 3.1 Flash-Lite | Phi-4 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| GPQA Diamond | 86.9% ↗ | 56.1% ↗ | +30.8 pt | Gemini 3.1 Flash-Lite |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 80% ↗epoch | 13.8% ↗epoch | +66.2 pt | Gemini 3.1 Flash-Lite |
| Only Gemini 3.1 Flash-Lite reports · 7 | ||||
| Humanity's Last Exam (no tools) | 16% ↗ | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 27.7% ↗epoch | 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 | — | — |
| SimpleQA Verified | 43.3% ↗ | not reported | — | — |
| Only Phi-4 reports · 8 | ||||
| MMLU | not reported | 84.8% ↗ | — | — |
| MMLU-Pro | not reported | 70.4% ↗ | — | — |
| HumanEval | not reported | 82.6% ↗ | — | — |
| LMArena Elo | not reported | 1216.6 ↗ | — | — |
| ArenaHard | not reported | 75.4% ↗ | — | — |
| HumanEval+ | not reported | 82.8% ↗ | — | — |
| IFEval | not reported | 63% ↗ | — | — |
| MATH | not reported | 80.4% ↗ | — | — |
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 Phi-4 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 | Phi-4 | Edge |
|---|---|---|---|
| Context window | 1.0M tokens | 16K tokens | Gemini 3.1 Flash-Lite |
| Max output | 66K tokens | 16K tokens | Gemini 3.1 Flash-Lite |
| Input price / 1M | $0.25 ↗ | — | — |
| Output price / 1M | $1.5 ↗ | — | — |
| Cached input / 1M | $0.025 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.75 | — | — |
| Modalities | text · vision · audio | text | Gemini 3.1 Flash-Lite |
| Released | 2026-03-03 | 2024-12-12 | — |
| Cited benchmark scores | 10 | 11 | — |
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
Phi-4 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 Phi-4 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.