Model comparison
GPT-5.2 vs GPT-5.5
Head-to-head evidence from 23 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.2 #64 (Estimated); GPT-5.5 #9 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.2 and GPT-5.5 share 23 comparable benchmark results. 6 of 8 categories are comparable. 5 results are unique to GPT-5.2; 34 to GPT-5.5.
Updated July 23, 2026- Shared results
- 23
- GPT-5.2 only
- 5
- GPT-5.5 only
- 34
- Comparable categories
- 6 / 8
Pick GPT-5.5 if you want the stronger benchmark profile. GPT-5.2 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 23 shared benchmark results across 7 evidence categories; 6 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 58.43. 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 reasoning, where it averages 85 against 52.9. The single biggest benchmark swing on the page is ARC-AGI-2, 52.9% to 85%. GPT-5.2 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 $1.75 input / $14.00 output per 1M tokens for GPT-5.2. That is roughly 2.1x on output cost alone. GPT-5.5 gives you the larger context window at 1M, compared with 400K for GPT-5.2.
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 | GPT-5.2 | Δ | GPT-5.5 |
|---|---|---|---|
| Knowledge | GPT-5.292.4 | Margin← 34.6 | GPT-5.557.8 |
| Reasoning | GPT-5.252.9 | Margin→ 32.1 | GPT-5.585.0 |
| Agentic | GPT-5.255.7 | Margin→ 25.9 | GPT-5.581.6 |
| Math | GPT-5.235.2 | Margin→ 12.4 | GPT-5.547.6 |
| Coding | GPT-5.270.6 | Margin← 12.0 | GPT-5.558.6 |
| Multimodal | GPT-5.280.4 | Margin← 10.0 | GPT-5.570.4 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
ARC-AGI-2
ReasoningA 52.9%B 85%Winner: GPT-5.5Δ 32.1ARC-AGI-2: GPT-5.2 scored 52.9%; GPT-5.5 scored 85%. GPT-5.5 wins this benchmark. - Source ↗
OSWorld-Verified
AgenticA 47.3%B 78.7%Winner: GPT-5.5Δ 31.4OSWorld-Verified: GPT-5.2 scored 47.3%; GPT-5.5 scored 78.7%. GPT-5.5 wins this benchmark. - Source ↗
BrowseComp
AgenticA 65.8%B 84.4%Winner: GPT-5.5Δ 18.6BrowseComp: GPT-5.2 scored 65.8%; GPT-5.5 scored 84.4%. GPT-5.5 wins this benchmark. - Source ↗
FrontierMath v2 (Tier 4)
MathA 18.800%B 35.400%Winner: GPT-5.5Δ 16.6FrontierMath v2 (Tier 4): GPT-5.2 scored 18.800%; 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): GPT-5.2 scored 40.700%; GPT-5.5 scored 51.700%. GPT-5.5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-5.2 | GPT-5.5 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.2$1.75 input / $14 output | GPT-5.5$5 input / $30 output | GPT-5.2 has the lower combined listed price. |
| Generation speedtokens per second | GPT-5.273 tok/s | GPT-5.5Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-5.2130.34 s | GPT-5.5Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-5.2400K | GPT-5.51M | GPT-5.5 lists the larger context window. |
Benchmark Deep Dive
AgenticGPT-5.5 wins24 benchmarks
| Benchmark | GPT-5.2 | GPT-5.5 | Result |
|---|---|---|---|
| BrowseCompSource | 65.8% | 84.4% | GPT-5.5 leads |
| OSWorld-VerifiedSource | 47.3% | 78.7% | GPT-5.5 leads |
| τ²-bench resultsSource | 84.8% | 93.9% | GPT-5.5 leads |
| Gert LabsSource | 46.54% | 72.93% | GPT-5.5 leads |
| JobBenchSource | 34.3% | 42.7% | GPT-5.5 leads |
| Terminal-Bench 2.0Source | — | 82% | Not comparable |
| CyberGymSource | — | 81.8% | Not comparable |
| 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 |
| ResearchClawBenchSource | — | 17.0% | 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 |
CodingGPT-5.2 wins10 benchmarks
| Benchmark | GPT-5.2 | GPT-5.5 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 80% | — | Not comparable |
| SWE-bench ProSource | 55.6% | 58.6% | GPT-5.5 leads |
| Vibe Code BenchSource | 53.50% | 69.85% | GPT-5.5 leads |
| AA-SciCodeSource | 52.1% | 56.1% | GPT-5.5 leads |
| Terminal-Bench 2.0Source | — | 82.0% | Not comparable |
| React Native EvalsSource | — | 84.7% | Not comparable |
| cursorBench31Source | — | 59.2% | Not comparable |
| cursorBench32Source | — | 58.4% | Not comparable |
| AA Coding IndexSource | — | 74.9% | Not comparable |
| FrontierCode 1.1 MainSource | — | 43.0% | Not comparable |
ReasoningGPT-5.5 wins5 benchmarks
KnowledgeGPT-5.2 wins10 benchmarks
| Benchmark | GPT-5.2 | GPT-5.5 | Result |
|---|---|---|---|
| GPQASource | 92.4% | 93.6% | GPT-5.5 leads |
| Artificial Analysis Intelligence IndexSource | 42.2% | 54.8% | GPT-5.5 leads |
| AA-GPQA DiamondSource | 90.3% | 93.5% | GPT-5.5 leads |
| AA-HLESource | 35.4% | 44.3% | GPT-5.5 leads |
| AA-Omniscience IndexSource | -1.0% | 20.1% | GPT-5.5 leads |
| AA-Omniscience AccuracySource | 43.8% | 56.9% | GPT-5.5 leads |
| AA-Omniscience Hallucination RateSource | 79.7% | 85.5% | GPT-5.2 leads |
| GPQA-DSource | — | 93.6% | Not comparable |
| HLESource | — | 52.2% | Not comparable |
| HLE w/o toolsSource | — | 41.4% | Not comparable |
MathGPT-5.5 wins4 benchmarks
MultimodalGPT-5.2 wins8 benchmarks
| Benchmark | GPT-5.2 | GPT-5.5 | Result |
|---|---|---|---|
| MMMU-ProSource | 79.5% | 81.2% | GPT-5.5 leads |
| MathVisionSource | 83.0% | — | Not comparable |
| CharXivSource | 82.1% | — | Not comparable |
| V*Source | 75.9% | — | Not comparable |
| Design Arena WebsiteSource | 1224 | 1282 | GPT-5.5 leads |
| MMMU-Pro w/ PythonSource | — | 83.2% | Not comparable |
| OfficeQA ProSource | — | 54.1% | Not comparable |
| AA-MMMU-ProSource | — | 79.9% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | GPT-5.2 | GPT-5.5 | Result |
|---|---|---|---|
| AA-IFBenchSource | 75.4% | 75.9% | GPT-5.5 leads |
Frequently Asked Questions (7)
Which is better, GPT-5.2 or GPT-5.5?
GPT-5.5 is ahead on BenchLM's BenchAlign leaderboard, 73.51 to 58.43. The biggest single separator in this matchup is ARC-AGI-2, where the scores are 52.9% and 85%.
Which is better for knowledge tasks, GPT-5.2 or GPT-5.5?
GPT-5.2 has the edge for knowledge tasks in this comparison, averaging 92.4 versus 57.8. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.
Which is better for coding, GPT-5.2 or GPT-5.5?
GPT-5.2 has the edge for coding in this comparison, averaging 70.6 versus 58.6. Inside this category, Vibe Code Bench is the benchmark that creates the most daylight between them.
Which is better for math, GPT-5.2 or GPT-5.5?
GPT-5.5 has the edge for math in this comparison, averaging 47.6 versus 35.2. Inside this category, FrontierMath v2 (Tier 4) is the benchmark that creates the most daylight between them.
Which is better for reasoning, GPT-5.2 or GPT-5.5?
GPT-5.5 has the edge for reasoning in this comparison, averaging 85 versus 52.9. Inside this category, ARC-AGI-2 is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GPT-5.2 or GPT-5.5?
GPT-5.5 has the edge for agentic tasks in this comparison, averaging 81.6 versus 55.7. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, GPT-5.2 or GPT-5.5?
GPT-5.2 has the edge for multimodal and grounded tasks in this comparison, averaging 80.4 versus 70.4. Inside this category, Design Arena Website is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
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.