Model comparison
Claude Opus 4.5 vs GPT-5.2-Codex
Head-to-head evidence from 14 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Opus 4.5 #34 (Supported); GPT-5.2-Codex #58 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Opus 4.5 and GPT-5.2-Codex share 14 comparable benchmark results. 0 of 8 categories are comparable. 45 results are unique to Claude Opus 4.5; 1 to GPT-5.2-Codex.
Updated July 20, 2026- Shared results
- 14
- Claude Opus 4.5 only
- 45
- GPT-5.2-Codex only
- 1
- Comparable categories
- 0 / 8
Benchmark data for Claude Opus 4.5 and GPT-5.2-Codex is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 14 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Claude Opus 4.5 is priced at $5.00 input / $25.00 output per 1M tokens, versus $1.75 input / $14.00 output per 1M tokens for GPT-5.2-Codex. GPT-5.2-Codex has the larger context window at 400K, compared with 200K for Claude Opus 4.5.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Claude Opus 4.5 | Δ | GPT-5.2-Codex |
|---|---|---|---|
| Agentic | Claude Opus 4.562.6 | MarginNo overlap | GPT-5.2-CodexNot measured |
| Coding | Claude Opus 4.571.7 | MarginNo overlap | GPT-5.2-CodexNot measured |
| Reasoning | Claude Opus 4.564.4 | MarginNo overlap | GPT-5.2-CodexNot measured |
| Knowledge | Claude Opus 4.558.1 | MarginNo overlap | GPT-5.2-CodexNot measured |
| Math | Claude Opus 4.557.5 | MarginNo overlap | GPT-5.2-CodexNot measured |
| Multilingual | Claude Opus 4.585.7 | MarginNo overlap | GPT-5.2-CodexNot measured |
| Multimodal | Claude Opus 4.569.9 | MarginNo overlap | GPT-5.2-CodexNot measured |
| Inst. Following | Claude Opus 4.569.5 | MarginNo overlap | GPT-5.2-CodexNot measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Opus 4.5 | GPT-5.2-Codex | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Opus 4.5$5 input / $25 output | GPT-5.2-Codex$1.75 input / $14 output | GPT-5.2-Codex has the lower combined listed price. |
| Generation speedtokens per second | Claude Opus 4.546 tok/s | GPT-5.2-Codex123 tok/s | GPT-5.2-Codex has the higher measured throughput. |
| First-answer latencyseconds to first token | Claude Opus 4.51.01 s | GPT-5.2-Codex87.34 s | Claude Opus 4.5 reaches the first token sooner. |
| Context windowmaximum listed tokens | Claude Opus 4.5200K | GPT-5.2-Codex400K | GPT-5.2-Codex lists the larger context window. |
Benchmark Deep Dive
Agentic16 benchmarks
| Benchmark | Claude Opus 4.5 | GPT-5.2-Codex | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 59.3% | — | Not comparable |
| OSWorld-VerifiedSource | 66.3% | — | Not comparable |
| OSWorldSource | 66.3% | — | Not comparable |
| Claw-EvalSource | 59.6% | — | Not comparable |
| QwenClawBenchSource | 52.3% | — | Not comparable |
| τ³-bench resultsSource | 70.2% | — | Not comparable |
| VITA-BenchSource | 23.3% | — | Not comparable |
| DeepPlanningSource | 26.4% | — | Not comparable |
| ToolathlonSource | 43.5% | — | Not comparable |
| MCP AtlasSource | 42.3% | — | Not comparable |
| MCP-TasksSource | 71.8% | — | Not comparable |
| WideResearchSource | 76.4% | — | Not comparable |
| CyberGymSource | 50.6% | — | Not comparable |
| τ²-bench resultsSource | 86.3% | 92.1% | GPT-5.2-Codex leads |
| Gert LabsSource | 64.23% | 51.79% | Claude Opus 4.5 leads |
| JobBenchSource | 32.3% | 26.0% | Claude Opus 4.5 leads |
Coding7 benchmarks
| Benchmark | Claude Opus 4.5 | GPT-5.2-Codex | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 80.9% | — | Not comparable |
| LiveCodeBench v6Source | 84.8% | — | Not comparable |
| SWE-bench ProSource | 57.1% | — | Not comparable |
| SWE MultilingualSource | 77.5% | — | Not comparable |
| NL2RepoSource | 43.2% | — | Not comparable |
| AA-SciCodeSource | 47.0% | 54.6% | GPT-5.2-Codex leads |
| Vibe Code BenchSource | — | 37.91% | Not comparable |
Reasoning4 benchmarks
Knowledge13 benchmarks
| Benchmark | Claude Opus 4.5 | GPT-5.2-Codex | Result |
|---|---|---|---|
| GPQASource | 87% | — | Not comparable |
| SuperGPQASource | 70.6% | — | Not comparable |
| MMLU-ProSource | 89.5% | — | Not comparable |
| MMLU-ReduxSource | 96.6% | — | Not comparable |
| C-EvalSource | 92.2% | — | Not comparable |
| HLESource | 30.8% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 34.7% | 40.1% | GPT-5.2-Codex leads |
| AA-GPQA DiamondSource | 81.0% | 89.9% | GPT-5.2-Codex leads |
| AA-HLESource | 12.9% | 33.5% | GPT-5.2-Codex leads |
| AA-Omniscience IndexSource | -3.9% | -2.5% | GPT-5.2-Codex leads |
| AA-Omniscience AccuracySource | 40.7% | 40.7% | Tie |
| AA-Omniscience Hallucination RateSource | 75.4% | 72.8% | GPT-5.2-Codex leads |
| AA MMLU-ProSource | 88.9% | — | Not comparable |
Math7 benchmarks
| Benchmark | Claude Opus 4.5 | GPT-5.2-Codex | Result |
|---|---|---|---|
| AIME26Source | 95.1% | — | Not comparable |
| HMMT Feb 2025Source | 92.9% | — | Not comparable |
| HMMT Nov 2025Source | 93.3% | — | Not comparable |
| HMMT Feb 2026Source | 85.3% | — | Not comparable |
| MMAnswerBenchSource | 84.0% | — | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | 20.690% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 4.167% | — | Not comparable |
Multilingual2 benchmarks
Multimodal8 benchmarks
| Benchmark | Claude Opus 4.5 | GPT-5.2-Codex | Result |
|---|---|---|---|
| MMMU-ProSource | 70.6% | — | Not comparable |
| MathVisionSource | 74.3% | — | Not comparable |
| CharXivSource | 68.5% | — | Not comparable |
| VideoMMMUSource | 84.4% | — | Not comparable |
| ScreenSpot ProSource | 45.7% | — | Not comparable |
| V*Source | 67.0% | — | Not comparable |
| AA-MMMU-ProSource | 71.2% | 76.3% | GPT-5.2-Codex leads |
| Design Arena WebsiteSource | 1279 | — | Not comparable |
Frequently Asked Questions (3)
Can I compare Claude Opus 4.5 and GPT-5.2-Codex on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for Claude Opus 4.5 and GPT-5.2-Codex today?
Claude Opus 4.5: $5.00 input / $25.00 output per 1M tokens GPT-5.2-Codex: $1.75 input / $14.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Related Comparisons
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.