Data points: 90
The readout for Claude Opus 4.6 and GPT-5.2 Codex, before the detailed comparison sheet.
Decision read
Claude Opus 4.6
Claude Opus 4.6 currently has the stronger profile, with verified wins split 4 to 2.
Evidence depth
90 data points
Includes 8 benchmark rows, 2 audit samples, and 9 provider examples.
Selection signal
Start with Claude Opus 4.6
The charts below split 19 high-signal samples across speed, scores, and audit health.
Model compare Claude Opus 4.6 vs GPT-5.2 Codexclaude-opus-4-6-vs-gpt-5-2-codex | Model A Claude Opus 4.6 | Model B GPT-5.2 Codex |
|---|---|---|
| Overall leader | Leading | Contender |
| Verified metric wins | 4 wins | 2 wins |
| Where it leads | Cheapest input price, Free providers, Provider coverage, Recent tests | Average speed, First-token latency |
| Model metadata | Claude Opus 4.6 exposes 1M tokens; notable signals: Text input, Image input, File input, Text output. | GPT-5.2 Codex exposes 400K tokens; notable signals: Text input, Image input, Text output, Tool calling. |
| Developer | Anthropic | OpenAI |
| Context window | 1M tokens | 400K tokens |
| Max output | 128K tokens | 128K tokens |
| Released | Apr 2026 | Jan 2026 |
| Modalities | Input TextImageFile Output Text | Input TextImage Output Text |
| Features | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputText outputTool callingStructured outputsJSON modeReasoning |
| Parameters | No data | No data |
| Tokenizer | Claude | GPT |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | anthropic/claude-opus-4.6-fast | openai/gpt-5.2-codex |
| References | No data | No data |
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
| Metric | Claude Opus 4.6 | GPT-5.2 Codex |
|---|---|---|
| SciCode | 45.7%#20 | 54.6%#5 |
| GPQA | 84.0%#38 | 89.9%#10 |
| HLE | 18.6%#43 | 33.5%#11 |
| Time to first answer token | 1.44 s#34 | 1.17 s#27 |
| Input price | $5.00/M#41 | $1.75/M#35 |
| Output speed | 44.9 tok/s#96 | 125.5 tok/s#40 |
| Output price | $25.00/M#47 | $14.00/M#43 |
| Time to first token | 1.44 s#57 | 1.17 s#44 |
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | Claude Opus 4.6 | GPT-5.2 Codex |
|---|---|---|
BUZZWinner: Claude Opus 4.6 | Claude Opus 4.6 claude-opus-4-6 Audit score 97 10010010088 | GPT-5.2 Codex gpt-5.2-codex No audit yet |
钠 APIWinner: Claude Opus 4.6 | Claude Opus 4.6 claude-opus-4-6 Audit score 80 668470100 | GPT-5.2 Codex gpt-5.2-codex No audit yet |
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | Claude Opus 4.6 | GPT-5.2 Codex |
|---|---|---|
钠 API25 tests | Claude Opus 4.6 speed / latency 42 tok/s / 2282ms input / output No data | GPT-5.2 Codex speed / latency 55 tok/s / 5209ms input / output No data |
Rnglg2 API15 tests | Claude Opus 4.6 speed / latency 57 tok/s / 3926ms input / output No data | GPT-5.2 Codex speed / latency N/A / N/A input / output No data |
巨量API15 tests | Claude Opus 4.6 speed / latency 24 tok/s / 7946ms input / output No data | GPT-5.2 Codex speed / latency 67 tok/s / 4708ms input / output No data |
GOU API10 tests | Claude Opus 4.6 speed / latency 51 tok/s / 9040ms input / output No data | GPT-5.2 Codex speed / latency N/A / N/A input / output No data |
发现AI7 tests | Claude Opus 4.6 speed / latency 39 tok/s / 9397ms input / output No data | GPT-5.2 Codex speed / latency N/A / N/A input / output No data |
Claude Opus 4.6 claude-opus-4.6 speed / latency No data input / output $0/M / $0/M | GPT-5.2 Codex gpt-5.2-codex speed / latency No data input / output $0.140/M / $1.12/M | |
Claude Opus 4.6 claude-opus-4-6-thinking speed / latency No data input / output $0.060/M / $0.060/M | GPT-5.2 Codex gpt-5.2-codex speed / latency No data input / output $0.010/M / $0.010/M | |
Claude Opus 4.6 claude-opus-4-6 speed / latency No data input / output $0.040/M / $0.200/M | GPT-5.2 Codex gpt-5.2-codex speed / latency No data input / output $0.020/M / $0.160/M | |
Claude Opus 4.6 claude-opus-4-6 speed / latency No data input / output $0.068/M / $0.342/M | GPT-5.2 Codex gpt-5.2-codex-xhigh speed / latency No data input / output $0.024/M / $0.192/M |
This report only uses LMSpeed data for Claude Opus 4.6 and GPT-5.2 Codex: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Guidance | Claude Opus 4.6 | GPT-5.2 Codex |
|---|---|---|
| When to choose each model | Claude Opus 4.6 Claude Opus 4.6 is stronger when you prioritize Cheapest input price, Free providers, Provider coverage, Recent tests. | GPT-5.2 Codex GPT-5.2 Codex is stronger when you prioritize Average speed, First-token latency. |
TL;DR: Claude Opus 4.6 leads across 90 verifiable data points, including pricing, speed, latency, benchmarks, and provider examples.
Continue from Claude Opus 4.6 vs GPT-5.2 Codex into nearby model comparisons with enough verified LMSpeed data.
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
