Model comparison
Claude Opus 4.6 vs GPT-5.5
Head-to-head evidence from 31 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Claude Opus 4.6 #16 (Supported); GPT-5.5 #9 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Claude Opus 4.6 and GPT-5.5 share 31 comparable benchmark results. 5 of 8 categories are comparable. 15 results are unique to Claude Opus 4.6; 26 to GPT-5.5.
Updated July 23, 2026- Shared results
- 31
- Claude Opus 4.6 only
- 15
- GPT-5.5 only
- 26
- Comparable categories
- 5 / 8
Pick GPT-5.5 if you want the stronger benchmark profile. Claude Opus 4.6 only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 31 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-5.5 is clearly ahead on the BenchAlign aggregate, 73.51 to 68.59. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.5's sharpest advantage is in mathematics, where it averages 47.6 against 36.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 65.4% to 82%. Claude Opus 4.6 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
GPT-5.5 is also the more expensive model on tokens at $5.00 input / $30.00 output per 1M tokens, versus $5.00 input / $25.00 output per 1M tokens for Claude Opus 4.6. GPT-5.5 is the reasoning model in the pair, while Claude Opus 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.
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 4.6 | Δ | GPT-5.5 |
|---|---|---|---|
| Math | Claude Opus 4.636.3 | Margin→ 11.3 | GPT-5.547.6 |
| Knowledge | Claude Opus 4.669.1 | Margin← 11.3 | GPT-5.557.8 |
| Coding | Claude Opus 4.668.1 | Margin← 9.5 | GPT-5.558.6 |
| Agentic | Claude Opus 4.673.0 | Margin→ 8.6 | GPT-5.581.6 |
| Multimodal | Claude Opus 4.677.3 | Margin← 6.9 | GPT-5.570.4 |
| Reasoning | Claude Opus 4.6Not measured | MarginNo overlap | GPT-5.585.0 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 65.4%B 82%Winner: GPT-5.5Δ 16.6Terminal-Bench 2.0: Claude Opus 4.6 scored 65.4%; GPT-5.5 scored 82%. GPT-5.5 wins this benchmark. - Source ↗
FrontierMath v2 (Tier 4)
MathA 22.900%B 35.400%Winner: GPT-5.5Δ 12.5FrontierMath v2 (Tier 4): Claude Opus 4.6 scored 22.900%; GPT-5.5 scored 35.400%. GPT-5.5 wins this benchmark. - Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 40.700%B 51.700%Winner: GPT-5.5Δ 11FrontierMath v2 (Tiers 1-3): Claude Opus 4.6 scored 40.700%; GPT-5.5 scored 51.700%. GPT-5.5 wins this benchmark. - Source ↗
OSWorld-Verified
AgenticA 72.7%B 78.7%Winner: GPT-5.5Δ 6OSWorld-Verified: Claude Opus 4.6 scored 72.7%; GPT-5.5 scored 78.7%. GPT-5.5 wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 53.4%B 58.6%Winner: GPT-5.5Δ 5.2SWE-bench Pro: Claude Opus 4.6 scored 53.4%; GPT-5.5 scored 58.6%. GPT-5.5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Opus 4.6 | GPT-5.5 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Opus 4.6$5 input / $25 output | GPT-5.5$5 input / $30 output | Claude Opus 4.6 has the lower combined listed price. |
| Generation speedtokens per second | Claude Opus 4.640 tok/s | GPT-5.5Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Opus 4.61.78 s | GPT-5.5Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Opus 4.61M | GPT-5.51M | Listed context windows are equal. |
Benchmark Deep Dive
AgenticGPT-5.5 wins26 benchmarks
| Benchmark | Claude Opus 4.6 | GPT-5.5 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 65.4% | 82% | GPT-5.5 leads |
| BrowseCompSource | 83.7% | 84.4% | GPT-5.5 leads |
| OSWorld-VerifiedSource | 72.7% | 78.7% | GPT-5.5 leads |
| τ²-bench resultsSource | 84.8% | 93.9% | GPT-5.5 leads |
| Claw-EvalSource | 70.4% | — | Not comparable |
| DeepSearchQASource | 73.7% | — | Not comparable |
| CyberGymSource | 66.6% | 81.8% | GPT-5.5 leads |
| Gert LabsSource | 61.85% | 72.93% | GPT-5.5 leads |
| ResearchClawBenchSource | 19.9% | 17.0% | Claude Opus 4.6 leads |
| JobBenchSource | 36.7% | 42.7% | GPT-5.5 leads |
| MCP AtlasSource | — | 75.3% | Not comparable |
| ToolathlonSource | — | 55.6% | Not comparable |
| AA Agentic IndexSource | — | 44.9% | Not comparable |
| APEX-Agents-AASource | — | 37.7% | Not comparable |
| GDPval-AASource | — | 49.5% | Not comparable |
| GDPval-AASource | — | 1490 | Not comparable |
| OSWorld 2.0Source | — | 13.0% | Not comparable |
| ExploitGymSource | — | 13.4% | Not comparable |
| AA BriefcaseSource | — | 1154 | Not comparable |
| AA AutomationBenchSource | — | 42.1% | Not comparable |
| AA EnterpriseOps-GymSource | — | 46.6% | Not comparable |
| AA Harvey LABSource | — | 86.3% | Not comparable |
| AA ITBenchSource | — | 45.8% | Not comparable |
| AA Tau3 BankingSource | — | 31.3% | Not comparable |
| terminalBenchHardSource | — | 60.6% | Not comparable |
| aaTerminalBench21Source | — | 84.3% | Not comparable |
CodingClaude Opus 4.6 wins13 benchmarks
| Benchmark | Claude Opus 4.6 | GPT-5.5 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 80.8% | — | Not comparable |
| SWE-bench Verified*Source | 75.6% | — | Not comparable |
| LiveCodeBench ProSource | 70.7% | — | Not comparable |
| SWE-bench ProSource | 53.4% | 58.6% | GPT-5.5 leads |
| SWE-RebenchSource | 65.3% | — | Not comparable |
| React Native EvalsSource | 84.1% | 84.7% | GPT-5.5 leads |
| Vibe Code BenchSource | 57.57% | 69.85% | GPT-5.5 leads |
| AA-SciCodeSource | 45.7% | 56.1% | GPT-5.5 leads |
| FrontierCode 1.1 MainSource | 26.9% | 43.0% | GPT-5.5 leads |
| Terminal-Bench 2.0Source | — | 82.0% | Not comparable |
| cursorBench31Source | — | 59.2% | Not comparable |
| cursorBench32Source | — | 58.4% | Not comparable |
| AA Coding IndexSource | — | 74.9% | Not comparable |
Reasoning5 benchmarks
KnowledgeClaude Opus 4.6 wins15 benchmarks
| Benchmark | Claude Opus 4.6 | GPT-5.5 | Result |
|---|---|---|---|
| GPQASource | 91.3% | 93.6% | GPT-5.5 leads |
| GPQA-DSource | 89.2% | 93.6% | GPT-5.5 leads |
| SuperGPQASource | 95% | — | Not comparable |
| MMLU-ProSource | 82% | — | Not comparable |
| MMLU-Pro (Arcee)Source | 89.1% | — | Not comparable |
| HLESource | 53% | 52.2% | Claude Opus 4.6 leads |
| HLE w/o toolsSource | 40% | 41.4% | GPT-5.5 leads |
| HealthBench HardSource | 14.8% | — | Not comparable |
| MedXpertQA (Text)Source | 52.1% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 37.8% | 54.8% | GPT-5.5 leads |
| AA-GPQA DiamondSource | 84.0% | 93.5% | GPT-5.5 leads |
| AA-HLESource | 18.6% | 44.3% | GPT-5.5 leads |
| AA-Omniscience IndexSource | 3.5% | 20.1% | GPT-5.5 leads |
| AA-Omniscience AccuracySource | 45.2% | 56.9% | GPT-5.5 leads |
| AA-Omniscience Hallucination RateSource | 76.0% | 85.5% | Claude Opus 4.6 leads |
MathGPT-5.5 wins4 benchmarks
MultimodalClaude Opus 4.6 wins8 benchmarks
| Benchmark | Claude Opus 4.6 | GPT-5.5 | Result |
|---|---|---|---|
| MMMU-ProSource | 77.3% | 81.2% | GPT-5.5 leads |
| ERQASource | 51.6% | — | Not comparable |
| ScreenSpot ProSource | 83.1% | — | Not comparable |
| MedXpertQA (MM)Source | 64.8% | — | Not comparable |
| AA-MMMU-ProSource | 72.5% | 79.9% | GPT-5.5 leads |
| Design Arena WebsiteSource | 1325 | 1282 | Claude Opus 4.6 leads |
| MMMU-Pro w/ PythonSource | — | 83.2% | Not comparable |
| OfficeQA ProSource | — | 54.1% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Claude Opus 4.6 | GPT-5.5 | Result |
|---|---|---|---|
| AA-IFBenchSource | 44.6% | 75.9% | GPT-5.5 leads |
Frequently Asked Questions (6)
Which is better, Claude Opus 4.6 or GPT-5.5?
GPT-5.5 is ahead on BenchLM's BenchAlign leaderboard, 73.51 to 68.59. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 65.4% and 82%.
Which is better for knowledge tasks, Claude Opus 4.6 or GPT-5.5?
Claude Opus 4.6 has the edge for knowledge tasks in this comparison, averaging 69.1 versus 57.8. Inside this category, AA-HLE is the benchmark that creates the most daylight between them.
Which is better for coding, Claude Opus 4.6 or GPT-5.5?
Claude Opus 4.6 has the edge for coding in this comparison, averaging 68.1 versus 58.6. Inside this category, FrontierCode 1.1 Main is the benchmark that creates the most daylight between them.
Which is better for math, Claude Opus 4.6 or GPT-5.5?
GPT-5.5 has the edge for math in this comparison, averaging 47.6 versus 36.3. Inside this category, FrontierMath v2 (Tier 4) is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Claude Opus 4.6 or GPT-5.5?
GPT-5.5 has the edge for agentic tasks in this comparison, averaging 81.6 versus 73. 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 Opus 4.6 or GPT-5.5?
Claude Opus 4.6 has the edge for multimodal and grounded tasks in this comparison, averaging 77.3 versus 70.4. 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.