Model comparison
Claude Sonnet 4.5 vs GPT-5.2-Codex
Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Sonnet 4.5 #96 (Estimated); GPT-5.2-Codex #58 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Sonnet 4.5 and GPT-5.2-Codex share 2 comparable benchmark results. 0 of 8 categories are comparable. 10 results are unique to Claude Sonnet 4.5; 13 to GPT-5.2-Codex.
Updated July 20, 2026- Shared results
- 2
- Claude Sonnet 4.5 only
- 10
- GPT-5.2-Codex only
- 13
- Comparable categories
- 0 / 8
Benchmark data for Claude Sonnet 4.5 and GPT-5.2-Codex is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 1 evidence category; 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 Sonnet 4.5 is priced at $3.00 input / $15.00 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 Sonnet 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 Sonnet 4.5 | Δ | GPT-5.2-Codex |
|---|---|---|---|
| Agentic | Claude Sonnet 4.555.4 | MarginNo overlap | GPT-5.2-CodexNot measured |
| Coding | Claude Sonnet 4.577.2 | MarginNo overlap | GPT-5.2-CodexNot measured |
| Reasoning | Claude Sonnet 4.513.6 | MarginNo overlap | GPT-5.2-CodexNot measured |
| Knowledge | Claude Sonnet 4.583.4 | MarginNo overlap | GPT-5.2-CodexNot measured |
| Math | Claude Sonnet 4.511.2 | 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 Sonnet 4.5 | GPT-5.2-Codex | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Sonnet 4.5$3 input / $15 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 Sonnet 4.5Not available | GPT-5.2-Codex123 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Sonnet 4.5Not available | GPT-5.2-Codex87.34 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Sonnet 4.5200K | GPT-5.2-Codex400K | GPT-5.2-Codex lists the larger context window. |
Benchmark Deep Dive
Agentic6 benchmarks
| Benchmark | Claude Sonnet 4.5 | GPT-5.2-Codex | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 50% | — | Not comparable |
| OSWorld-VerifiedSource | 61.4% | — | Not comparable |
| VITA-BenchSource | 17.0% | — | Not comparable |
| Gert LabsSource | 48.51% | 51.79% | GPT-5.2-Codex leads |
| JobBenchSource | 27.7% | 26.0% | Claude Sonnet 4.5 leads |
| τ²-bench resultsSource | — | 92.1% | Not comparable |
Coding3 benchmarks
Reasoning3 benchmarks
Knowledge7 benchmarks
| Benchmark | Claude Sonnet 4.5 | GPT-5.2-Codex | Result |
|---|---|---|---|
| GPQASource | 83.4% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 40.1% | Not comparable |
| AA-GPQA DiamondSource | — | 89.9% | Not comparable |
| AA-HLESource | — | 33.5% | Not comparable |
| AA-Omniscience IndexSource | — | -2.5% | Not comparable |
| AA-Omniscience AccuracySource | — | 40.7% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 72.8% | Not comparable |
Math3 benchmarks
Multimodal2 benchmarks
Inst. Following1 benchmarks
| Benchmark | Claude Sonnet 4.5 | GPT-5.2-Codex | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 77.6% | Not comparable |
Frequently Asked Questions (3)
Can I compare Claude Sonnet 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 Sonnet 4.5 and GPT-5.2-Codex today?
Claude Sonnet 4.5: $3.00 input / $15.00 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.