modelgrep

Anthropic: Claude Opus 4.7 vs OpenAI: GPT-5.2-Codex

anthropic logoAnthropic: Claude Opus 4.7anthropic/claude-opus-4.7VSopenai logoOpenAI: GPT-5.2-Codexopenai/gpt-5.2-codex

Anthropic: Claude Opus 4.7 wins on more metrics (6 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricAnthropic: Claude Opus 4.7OpenAI: GPT-5.2-Codex
Intelligence Index53.5✓40.1
Coding Index73.6✓—
GPQA Diamond91%✓90%
Design Arena Elo1334✓—
Speed (tokens/sec)5964✓
Latency1.4s✓1.6s
Input price /M$5.00$1.75✓
Output price /M$25.00$14.00✓
Context window1M✓400K
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSONVision
Anthropic: Claude Opus 4.7 details →OpenAI: GPT-5.2-Codex details →