modelgrep

Anthropic: Claude Opus 4.8 vs Google: Gemini 3.1 Pro Preview

Anthropic: Claude Opus 4.8 wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricAnthropic: Claude Opus 4.8Google: Gemini 3.1 Pro Preview
Intelligence Index61.441.3
Coding Index56.739.4
GPQA Diamond92%89%
Design Arena Elo13721345
Speed (tokens/sec)5789
Latency1.4s3.4s
Input price /M$5.00$2.00
Output price /M$25.00$12.00
Context window1M1.0M
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSONVisionAudio