Quality
Known Good Index and the capability indices, side by side
Each index is min-max normalised across tracked models and scaled 0–100 from published evaluations. We do not run these evaluations.
| Metric | Google: Gemini 3.1 Pro Preview | Microsoft: Phi 4 |
|---|---|---|
| Known Good Index | 96 | 33 |
| Mathematics Index | 96 | 39 |
| Science Index | 99 | 53 |
| Reasoning Index | 100 | 47 |
| Agentic Index | 88 | — |
| Openness Index | 5 | 60 |
Quality Breakdown
Every evaluation both models report a published score for
Bar = Google: Gemini 3.1 Pro Preview · marker = Microsoft: Phi 4 · scores ingested from Epoch AI (CC-BY 4.0)
Right-hand figures read Google: Gemini 3.1 Pro Preview / Microsoft: Phi 4. Google: Gemini 3.1 Pro Preview leads on 2 of 2, Microsoft: Phi 4 on 0.
Arena Elo
Human preference rating from blind pairwise votes
Elo from blind pairwise votes, ingested from Arena. Higher is better.
| Metric | Google: Gemini 3.1 Pro Preview | Microsoft: Phi 4 |
|---|---|---|
| Text Arena | 1,479 | 1,217 |
| Text Arena (style controlled) | 1,486 | 1,256 |
Price & Cost
Published API pricing by token type
USD per 1M tokens. Blended is a 3:1 input:output mix. Live from OpenRouter, cross-checked against models.dev. Lower is better.
| Metric | Google: Gemini 3.1 Pro Preview | Microsoft: Phi 4 |
|---|---|---|
| Input $/1M | $2.00 | $0.07 |
| Output $/1M | $12.00 | $0.14 |
| Blended $/1M | $4.50 | $0.09 |
| Cache read $/1M | $0.200 | — |
Context Window
Maximum input accepted and maximum output emitted
Provider-declared limits, from metadata via models.dev and OpenRouter. Higher is better.
| Metric | Google: Gemini 3.1 Pro Preview | Microsoft: Phi 4 |
|---|---|---|
| Context window | 1.05M | 16k |
| Max output tokens | 66k | 16k |
Speed & Latency
Median throughput and time to first token across hosting providers
Medians across all tracked providers, derived from OpenRouter endpoint telemetry.
| Metric | Google: Gemini 3.1 Pro Preview | Microsoft: Phi 4 |
|---|---|---|
| Output tokens/s | 104 | 56 |
| Time to first token | 2.9s | 0.2s |
Providers
Which hosts serve each model, and at what price and speed
| Provider | Google: Gemini 3.1 Pro Preview blended | Google: Gemini 3.1 Pro Preview tok/s | Microsoft: Phi 4 blended | Microsoft: Phi 4 tok/s |
|---|---|---|---|---|
| Google AI Studio | $2.25 | 163 | — | — |
| Google · first party | $2.25 | 99 | — | — |
| DeepInfra | — | — | $0.09 | 70 |
Per-host pricing and telemetry from OpenRouter. A dash means that host does not serve that model.