Model comparison
Claude Sonnet 4.6 vs GPT-5.4
Head-to-head evidence from 26 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-5.4 #8 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Sonnet 4.6 and GPT-5.4 share 26 comparable benchmark results. 5 of 8 categories are comparable. 7 results are unique to Claude Sonnet 4.6; 26 to GPT-5.4.
Updated July 20, 2026- Shared results
- 26
- Claude Sonnet 4.6 only
- 7
- GPT-5.4 only
- 26
- Comparable categories
- 5 / 8
Pick GPT-5.4 if you want the stronger benchmark profile. Claude Sonnet 4.6 only becomes the better choice if coding is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Confidence note. This is a partial-evidence comparison with 26 shared benchmark results across 7 evidence categories; 5 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
GPT-5.4 is clearly ahead on the BenchAlign aggregate, 74.24 to 65.07. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.4's sharpest advantage is in mathematics, where it averages 42.5 against 26.4. The single biggest benchmark swing on the page is FrontierMath v2 (Tier 4), 8.300% to 27.100%. Claude Sonnet 4.6 does hit back in coding, so the answer changes if that is the part of the workload you care about most.
GPT-5.4 is the reasoning model in the pair, while Claude Sonnet 4.6 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-5.4 gives you the larger context window at 1.05M, compared with 200K for Claude Sonnet 4.6.
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-5.4 |
|---|---|---|---|
| Math | Claude Sonnet 4.626.4 | Margin→ 16.1 | GPT-5.442.5 |
| Agentic | Claude Sonnet 4.665.2 | Margin→ 12.0 | GPT-5.477.2 |
| Coding | Claude Sonnet 4.669.1 | Margin← 11.4 | GPT-5.457.7 |
| Knowledge | Claude Sonnet 4.666.0 | Margin← 8.4 | GPT-5.457.6 |
| Multimodal | Claude Sonnet 4.677.4 | Margin← 4.2 | GPT-5.473.2 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
FrontierMath v2 (Tier 4)
MathA 8.300%B 27.100%Winner: GPT-5.4Δ 18.8FrontierMath v2 (Tier 4): Claude Sonnet 4.6 scored 8.300%; GPT-5.4 scored 27.100%. GPT-5.4 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 59.1%B 75.1%Winner: GPT-5.4Δ 16Terminal-Bench 2.0: Claude Sonnet 4.6 scored 59.1%; GPT-5.4 scored 75.1%. GPT-5.4 wins this benchmark. - Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 32.400%B 47.600%Winner: GPT-5.4Δ 15.2FrontierMath v2 (Tiers 1-3): Claude Sonnet 4.6 scored 32.400%; GPT-5.4 scored 47.600%. GPT-5.4 wins this benchmark. - Source ↗
CharXiv
MultimodalA 77.4%B 82.8%Winner: GPT-5.4Δ 5.4CharXiv: Claude Sonnet 4.6 scored 77.4%; GPT-5.4 scored 82.8%. GPT-5.4 wins this benchmark. - Source ↗
HLE
KnowledgeA 49%B 52.1%Winner: GPT-5.4Δ 3.1HLE: Claude Sonnet 4.6 scored 49%; GPT-5.4 scored 52.1%. GPT-5.4 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-5.4 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Sonnet 4.6$3 input / $15 output | GPT-5.4$2.5 input / $15 output | GPT-5.4 has the lower combined listed price. |
| Generation speedtokens per second | Claude Sonnet 4.644 tok/s | GPT-5.474 tok/s | GPT-5.4 has the higher measured throughput. |
| First-answer latencyseconds to first token | Claude Sonnet 4.61.48 s | GPT-5.4151.79 s | Claude Sonnet 4.6 reaches the first token sooner. |
| Context windowmaximum listed tokens | Claude Sonnet 4.6200K | GPT-5.41.05M | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
AgenticGPT-5.4 wins18 benchmarks
| Benchmark | Claude Sonnet 4.6 | GPT-5.4 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 59.1% | 75.1% | GPT-5.4 leads |
| OSWorld-VerifiedSource | 72.1% | 75% | GPT-5.4 leads |
| Claw-EvalSource | 67.8% | 60.3% | Claude Sonnet 4.6 leads |
| CyberGymSource | 65.2% | 79.0% | GPT-5.4 leads |
| τ²-bench resultsSource | 79.5% | 87.1% | GPT-5.4 leads |
| Gert LabsSource | 62.92% | 64.89% | GPT-5.4 leads |
| OSWorld 2.0Source | 8.3% | — | Not comparable |
| JobBenchSource | 36.9% | 38.9% | GPT-5.4 leads |
| BrowseCompSource | — | 82.7% | Not comparable |
| MCP AtlasSource | — | 70.6% | Not comparable |
| ToolathlonSource | — | 54.6% | Not comparable |
| DeepSearchQASource | — | 73.6% | Not comparable |
| AA Agentic IndexSource | — | 41.1% | Not comparable |
| APEX-Agents-AASource | — | 33.3% | Not comparable |
| GDPval-AASource | — | 44.7% | Not comparable |
| GDPval-AASource | — | 1395 | Not comparable |
| ResearchClawBenchSource | — | 15.3% | Not comparable |
| ExploitGymSource | — | 6.0% | Not comparable |
CodingClaude Sonnet 4.6 wins10 benchmarks
| Benchmark | Claude Sonnet 4.6 | GPT-5.4 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 79.6% | — | Not comparable |
| SWE-RebenchSource | 60.7% | — | Not comparable |
| React Native EvalsSource | 80.6% | 85.3% | GPT-5.4 leads |
| Vibe Code BenchSource | 51.48% | 67.42% | GPT-5.4 leads |
| cursorBench31Source | 48.8% | — | Not comparable |
| AA-SciCodeSource | 46.9% | 56.6% | GPT-5.4 leads |
| FrontierCode 1.1 MainSource | 24.3% | — | Not comparable |
| LiveCodeBench ProSource | — | 87.5% | Not comparable |
| SWE-bench ProSource | — | 57.7% | Not comparable |
| AA Coding IndexSource | — | 71.0% | Not comparable |
Reasoning2 benchmarks
KnowledgeClaude Sonnet 4.6 wins15 benchmarks
| Benchmark | Claude Sonnet 4.6 | GPT-5.4 | Result |
|---|---|---|---|
| GPQASource | 89.9% | 92.8% | GPT-5.4 leads |
| SuperGPQASource | 95% | — | Not comparable |
| MMLU-ProSource | 79.2% | — | Not comparable |
| HLESource | 49% | 52.1% | GPT-5.4 leads |
| Artificial Analysis Intelligence IndexSource | 35.9% | 51.4% | GPT-5.4 leads |
| AA-GPQA DiamondSource | 79.9% | 92.0% | GPT-5.4 leads |
| AA-HLESource | 13.2% | 41.6% | GPT-5.4 leads |
| AA-Omniscience IndexSource | -2.9% | 5.7% | GPT-5.4 leads |
| AA-Omniscience AccuracySource | 38.0% | 50.0% | GPT-5.4 leads |
| AA-Omniscience Hallucination RateSource | 65.9% | 88.6% | Claude Sonnet 4.6 leads |
| HLE w/o toolsSource | — | 39.8% | Not comparable |
| GPQA-DSource | — | 92.8% | Not comparable |
| HealthBench HardSource | — | 40.1% | Not comparable |
| MedXpertQA (Text)Source | — | 59.6% | Not comparable |
| HealthBench ProfessionalSource | — | 48.1% | Not comparable |
MathGPT-5.4 wins2 benchmarks
MultimodalClaude Sonnet 4.6 wins11 benchmarks
| Benchmark | Claude Sonnet 4.6 | GPT-5.4 | Result |
|---|---|---|---|
| CharXivSource | 77.4% | 82.8% | GPT-5.4 leads |
| AA-MMMU-ProSource | 70.6% | 78.4% | GPT-5.4 leads |
| Design Arena WebsiteSource | 1317 | 1252 | Claude Sonnet 4.6 leads |
| MMMU-ProSource | — | 81.2% | Not comparable |
| OfficeQA ProSource | — | 53.2% | Not comparable |
| MMMU-Pro w/ PythonSource | — | 82.1% | Not comparable |
| ERQASource | — | 65.4% | Not comparable |
| SimpleVQASource | — | 61.1% | Not comparable |
| ScreenSpot ProSource | — | 85.4% | Not comparable |
| ZeroBenchSource | — | 41.0% | Not comparable |
| MedXpertQA (MM)Source | — | 77.1% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Claude Sonnet 4.6 | GPT-5.4 | Result |
|---|---|---|---|
| AA-IFBenchSource | 41.2% | 73.9% | GPT-5.4 leads |
Frequently Asked Questions (6)
Which is better, Claude Sonnet 4.6 or GPT-5.4?
GPT-5.4 is ahead on BenchLM's BenchAlign leaderboard, 74.24 to 65.07. The biggest single separator in this matchup is FrontierMath v2 (Tier 4), where the scores are 8.300% and 27.100%.
Which is better for knowledge tasks, Claude Sonnet 4.6 or GPT-5.4?
Claude Sonnet 4.6 has the edge for knowledge tasks in this comparison, averaging 66 versus 57.6. Inside this category, AA-HLE is the benchmark that creates the most daylight between them.
Which is better for coding, Claude Sonnet 4.6 or GPT-5.4?
Claude Sonnet 4.6 has the edge for coding in this comparison, averaging 69.1 versus 57.7. Inside this category, Vibe Code Bench is the benchmark that creates the most daylight between them.
Which is better for math, Claude Sonnet 4.6 or GPT-5.4?
GPT-5.4 has the edge for math in this comparison, averaging 42.5 versus 26.4. Inside this category, FrontierMath v2 (Tier 4) is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Claude Sonnet 4.6 or GPT-5.4?
GPT-5.4 has the edge for agentic tasks in this comparison, averaging 77.2 versus 65.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Claude Sonnet 4.6 or GPT-5.4?
Claude Sonnet 4.6 has the edge for multimodal and grounded tasks in this comparison, averaging 77.4 versus 73.2. Inside this category, Design Arena Website 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.