Model comparison
Claude Sonnet 4.6 vs GPT-4o
Head-to-head evidence from 13 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Sonnet 4.6 #32 (Supported); GPT-4o #165 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Sonnet 4.6 and GPT-4o share 13 comparable benchmark results. 1 of 8 categories are comparable. 20 results are unique to Claude Sonnet 4.6; 0 to GPT-4o.
Updated July 20, 2026- Shared results
- 13
- Claude Sonnet 4.6 only
- 20
- GPT-4o only
- 0
- Comparable categories
- 1 / 8
Pick Claude Sonnet 4.6 if you want the stronger benchmark profile. GPT-4o only becomes the better choice if you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 13 shared benchmark results across 7 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Claude Sonnet 4.6 is clearly ahead on the BenchAlign aggregate, 65.07 to 41.49. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Sonnet 4.6's sharpest advantage is in mathematics, where it averages 26.4 against 0.3. The single biggest benchmark swing on the page is FrontierMath v2 (Tiers 1-3), 32.400% to 0.345%.
Claude Sonnet 4.6 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $2.50 input / $10.00 output per 1M tokens for GPT-4o. Claude Sonnet 4.6 gives you the larger context window at 200K, compared with 128K for GPT-4o.
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 4.6 | Δ | GPT-4o |
|---|---|---|---|
| Math | Claude Sonnet 4.626.4 | Margin← 26.1 | GPT-4o0.3 |
| Agentic | Claude Sonnet 4.665.2 | MarginNo overlap | GPT-4oNot measured |
| Coding | Claude Sonnet 4.669.1 | MarginNo overlap | GPT-4oNot measured |
| Knowledge | Claude Sonnet 4.666.0 | MarginNo overlap | GPT-4oNot measured |
| Multimodal | Claude Sonnet 4.677.4 | MarginNo overlap | GPT-4oNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 32.400%B 0.345%Winner: Claude Sonnet 4.6Δ 32.1FrontierMath v2 (Tiers 1-3): Claude Sonnet 4.6 scored 32.400%; GPT-4o scored 0.345%. Claude Sonnet 4.6 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Sonnet 4.6 | GPT-4o | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Sonnet 4.6$3 input / $15 output | GPT-4o$2.5 input / $10 output | GPT-4o has the lower combined listed price. |
| Generation speedtokens per second | Claude Sonnet 4.644 tok/s | GPT-4o131 tok/s | GPT-4o has the higher measured throughput. |
| First-answer latencyseconds to first token | Claude Sonnet 4.61.48 s | GPT-4o0.81 s | GPT-4o reaches the first token sooner. |
| Context windowmaximum listed tokens | Claude Sonnet 4.6200K | GPT-4o128K | Claude Sonnet 4.6 lists the larger context window. |
Benchmark Deep Dive
Agentic8 benchmarks
| Benchmark | Claude Sonnet 4.6 | GPT-4o | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 59.1% | — | Not comparable |
| OSWorld-VerifiedSource | 72.1% | — | Not comparable |
| Claw-EvalSource | 67.8% | — | Not comparable |
| CyberGymSource | 65.2% | — | Not comparable |
| τ²-bench resultsSource | 79.5% | 25.1% | Claude Sonnet 4.6 leads |
| Gert LabsSource | 62.92% | — | Not comparable |
| OSWorld 2.0Source | 8.3% | — | Not comparable |
| JobBenchSource | 36.9% | — | Not comparable |
Coding7 benchmarks
| Benchmark | Claude Sonnet 4.6 | GPT-4o | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 79.6% | — | Not comparable |
| SWE-RebenchSource | 60.7% | — | Not comparable |
| React Native EvalsSource | 80.6% | — | Not comparable |
| Vibe Code BenchSource | 51.48% | — | Not comparable |
| cursorBench31Source | 48.8% | — | Not comparable |
| AA-SciCodeSource | 46.9% | 33.3% | Claude Sonnet 4.6 leads |
| FrontierCode 1.1 MainSource | 24.3% | — | Not comparable |
Reasoning2 benchmarks
Knowledge10 benchmarks
| Benchmark | Claude Sonnet 4.6 | GPT-4o | Result |
|---|---|---|---|
| GPQASource | 89.9% | — | Not comparable |
| SuperGPQASource | 95% | — | Not comparable |
| MMLU-ProSource | 79.2% | — | Not comparable |
| HLESource | 49% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 35.9% | 11.2% | Claude Sonnet 4.6 leads |
| AA-GPQA DiamondSource | 79.9% | 54.3% | Claude Sonnet 4.6 leads |
| AA-HLESource | 13.2% | 3.3% | Claude Sonnet 4.6 leads |
| AA-Omniscience IndexSource | -2.9% | -10.7% | Claude Sonnet 4.6 leads |
| AA-Omniscience AccuracySource | 38.0% | 19.7% | Claude Sonnet 4.6 leads |
| AA-Omniscience Hallucination RateSource | 65.9% | 37.9% | GPT-4o leads |
MathClaude Sonnet 4.6 wins2 benchmarks
Multimodal3 benchmarks
Inst. Following1 benchmarks
| Benchmark | Claude Sonnet 4.6 | GPT-4o | Result |
|---|---|---|---|
| AA-IFBenchSource | 41.2% | 34.3% | Claude Sonnet 4.6 leads |
Frequently Asked Questions (2)
Which is better, Claude Sonnet 4.6 or GPT-4o?
Claude Sonnet 4.6 is ahead on BenchLM's BenchAlign leaderboard, 65.07 to 41.49. The biggest single separator in this matchup is FrontierMath v2 (Tiers 1-3), where the scores are 32.400% and 0.345%.
Which is better for math, Claude Sonnet 4.6 or GPT-4o?
Claude Sonnet 4.6 has the edge for math in this comparison, averaging 26.4 versus 0.3. Inside this category, FrontierMath v2 (Tiers 1-3) is the benchmark that creates the most daylight between them.
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.