Head-to-head · 5 models compared
Claude vs Gemini
Anthropic and Google between them account for 5 rated models on the OpenRating Index. Claude's strongest entry is Claude Opus 5 (max) at 63.4, against Gemini's Gemini 3.7 Flash (high) at 56.2. Both are scored on the same axes, with the same tests, below.
Who wins on each axis
Claude takes 1 of 3 axes, Gemini takes 2.
OpenRating Index
Claude
63.4
Claude: Claude Opus 5 (max) · composite 0–100
Output speed
Gemini
392 tok/s
Gemini: Gemini 3.7 Flash (high) · blended tok/s, fastest model
Cost / task
Gemini
$0.096
Gemini: Gemini 3.5 Flash-Lite · lowest model, per benchmark run
Every rated model, side by side
Sorted by OpenRating Index. Every figure is measured under the same standardised workload.
| Model | Provider | Index | Reasoning | Speed | Cost / task | Input / 1M |
|---|---|---|---|---|---|---|
| Claude Opus 5 (max) | Claude | 63.4 | 89.4 | 59 tok/s | $2.34 | $4.8 |
| Claude Fable 5 (with fallback) | Claude | 62.3 | 87.8 | 72 tok/s | $3.14 | $5.5 |
| Gemini 3.7 Flash (high) | Gemini | 56.2 | 75.8 | 392 tok/s | $0.40 | $0.3 |
| Claude 4.5 Haiku | Claude | 49.6 | 68.2 | 195 tok/s | $0.22 | $0.4 |
| Gemini 3.5 Flash-Lite | Gemini | 37.6 | 54.5 | 313 tok/s | $0.096 | $0.05 |
Put Claude and Gemini head to head yourself
Pick any combination of models and compare their full cost breakdown — reasoning, answer generation, cache overhead, and input payload — in the OpenRating comparison tool.
Open the comparison tool →