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: Gemma 3 27B | OpenAI: GPT-5.1 |
|---|---|---|
| Known Good Index | 46 | 74 |
| Coding Index | — | 68 |
| Mathematics Index | 47 | 89 |
| Reasoning Index | 40 | 80 |
| Agentic Index | — | 61 |
| Openness Index | 60 | 5 |
Quality Breakdown
Every evaluation both models report a published score for
Bar = Google: Gemma 3 27B · marker = OpenAI: GPT-5.1 · scores ingested from Epoch AI (CC-BY 4.0), LiveBench (Apache-2.0)
Right-hand figures read Google: Gemma 3 27B / OpenAI: GPT-5.1. Google: Gemma 3 27B leads on 0 of 9, OpenAI: GPT-5.1 on 9.
Arena Elo
Human preference rating from blind pairwise votes
Elo from blind pairwise votes, ingested from Arena. Higher is better.
| Metric | Google: Gemma 3 27B | OpenAI: GPT-5.1 |
|---|---|---|
| Text Arena | — | 1,422 |
| Text Arena (style controlled) | — | 1,439 |
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: Gemma 3 27B | OpenAI: GPT-5.1 |
|---|---|---|
| Input $/1M | $0.08 | $1.25 |
| Output $/1M | $0.45 | $10.00 |
| Blended $/1M | $0.17 | $3.44 |
| Cache read $/1M | $0.040 | $0.125 |
Context Window
Maximum input accepted and maximum output emitted
Provider-declared limits, from metadata via models.dev and OpenRouter. Higher is better.
| Metric | Google: Gemma 3 27B | OpenAI: GPT-5.1 |
|---|---|---|
| Context window | 262k | 400k |
| Max output tokens | 131k | 128k |
Speed & Latency
Median throughput and time to first token across hosting providers
Medians across all tracked providers, derived from OpenRouter endpoint telemetry.
| Metric | Google: Gemma 3 27B | OpenAI: GPT-5.1 |
|---|---|---|
| Output tokens/s | 21 | 53 |
| Time to first token | 1.1s | 1.2s |
Providers
Which hosts serve each model, and at what price and speed
| Provider | Google: Gemma 3 27B blended | Google: Gemma 3 27B tok/s | OpenAI: GPT-5.1 blended | OpenAI: GPT-5.1 tok/s |
|---|---|---|---|---|
| Parasail | $0.17 | 37 | — | — |
| Phala | $0.23 | 20 | — | — |
| DeepInfra | $0.10 | 18 | — | — |
| Novita | $0.14 | 17 | — | — |
| Nebius | $0.15 | 15 | — | — |
| Azure · first party | — | — | $3.44 | 66 |
| OpenAI · first party | — | — | $1.72 | 44 |
Per-host pricing and telemetry from OpenRouter. A dash means that host does not serve that model.