Model comparison
Claude 4 Sonnet vs GPT-5.4
Head-to-head evidence from 15 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude 4 Sonnet #158 (Supported); GPT-5.4 #8 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude 4 Sonnet and GPT-5.4 share 15 comparable benchmark results. 1 of 8 categories are comparable. 1 result is unique to Claude 4 Sonnet; 37 to GPT-5.4.
Updated July 20, 2026- Shared results
- 15
- Claude 4 Sonnet only
- 1
- GPT-5.4 only
- 37
- Comparable categories
- 1 / 8
Pick GPT-5.4 if you want the stronger benchmark profile. Claude 4 Sonnet 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 15 shared benchmark results across 6 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
GPT-5.4 is clearly ahead on the BenchAlign aggregate, 74.24 to 42.79. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.4 is the reasoning model in the pair, while Claude 4 Sonnet 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 4 Sonnet.
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 4 Sonnet | Δ | GPT-5.4 |
|---|---|---|---|
| Coding | Claude 4 Sonnet72.7 | Margin← 15.0 | GPT-5.457.7 |
| Agentic | Claude 4 SonnetNot measured | MarginNo overlap | GPT-5.477.2 |
| Knowledge | Claude 4 SonnetNot measured | MarginNo overlap | GPT-5.457.6 |
| Math | Claude 4 SonnetNot measured | MarginNo overlap | GPT-5.442.5 |
| Multimodal | Claude 4 SonnetNot measured | MarginNo overlap | GPT-5.473.2 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude 4 Sonnet | GPT-5.4 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude 4 Sonnet$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 4 Sonnet40 tok/s | GPT-5.474 tok/s | GPT-5.4 has the higher measured throughput. |
| First-answer latencyseconds to first token | Claude 4 Sonnet1.33 s | GPT-5.4151.79 s | Claude 4 Sonnet reaches the first token sooner. |
| Context windowmaximum listed tokens | Claude 4 Sonnet200K | GPT-5.41.05M | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
Agentic17 benchmarks
| Benchmark | Claude 4 Sonnet | GPT-5.4 | Result |
|---|---|---|---|
| τ²-bench resultsSource | 52.3% | 87.1% | GPT-5.4 leads |
| Gert LabsSource | 39.66% | 64.89% | GPT-5.4 leads |
| JobBenchSource | 18.4% | 38.9% | GPT-5.4 leads |
| Terminal-Bench 2.0Source | — | 75.1% | Not comparable |
| CyberGymSource | — | 79.0% | Not comparable |
| BrowseCompSource | — | 82.7% | Not comparable |
| OSWorld-VerifiedSource | — | 75% | Not comparable |
| MCP AtlasSource | — | 70.6% | Not comparable |
| ToolathlonSource | — | 54.6% | Not comparable |
| Claw-EvalSource | — | 60.3% | 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 4 Sonnet wins7 benchmarks
| Benchmark | Claude 4 Sonnet | GPT-5.4 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 72.7% | — | Not comparable |
| AA-SciCodeSource | 37.3% | 56.6% | GPT-5.4 leads |
| LiveCodeBench ProSource | — | 87.5% | Not comparable |
| SWE-bench ProSource | — | 57.7% | Not comparable |
| React Native EvalsSource | — | 85.3% | Not comparable |
| Vibe Code BenchSource | — | 67.42% | Not comparable |
| AA Coding IndexSource | — | 71.0% | Not comparable |
Reasoning2 benchmarks
Knowledge13 benchmarks
| Benchmark | Claude 4 Sonnet | GPT-5.4 | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 25.5% | 51.4% | GPT-5.4 leads |
| AA-GPQA DiamondSource | 68.3% | 92.0% | GPT-5.4 leads |
| AA-HLESource | 4.0% | 41.6% | GPT-5.4 leads |
| AA-Omniscience IndexSource | -9.2% | 5.7% | GPT-5.4 leads |
| AA-Omniscience AccuracySource | 22.4% | 50.0% | GPT-5.4 leads |
| AA-Omniscience Hallucination RateSource | 40.8% | 88.6% | Claude 4 Sonnet leads |
| GPQASource | — | 92.8% | Not comparable |
| HLESource | — | 52.1% | Not comparable |
| 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 |
Math2 benchmarks
Multimodal11 benchmarks
| Benchmark | Claude 4 Sonnet | GPT-5.4 | Result |
|---|---|---|---|
| AA-MMMU-ProSource | 62.4% | 78.4% | GPT-5.4 leads |
| Design Arena WebsiteSource | 1178 | 1252 | GPT-5.4 leads |
| MMMU-ProSource | — | 81.2% | Not comparable |
| OfficeQA ProSource | — | 53.2% | Not comparable |
| MMMU-Pro w/ PythonSource | — | 82.1% | Not comparable |
| CharXivSource | — | 82.8% | 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 4 Sonnet | GPT-5.4 | Result |
|---|---|---|---|
| AA-IFBenchSource | 45.4% | 73.9% | GPT-5.4 leads |
Frequently Asked Questions (2)
Which is better, Claude 4 Sonnet or GPT-5.4?
GPT-5.4 is ahead on BenchLM's BenchAlign leaderboard, 74.24 to 42.79.
Which is better for coding, Claude 4 Sonnet or GPT-5.4?
Claude 4 Sonnet has the edge for coding in this comparison, averaging 72.7 versus 57.7. Inside this category, AA-SciCode 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.