Model comparison
Claude Opus 4.8 vs GPT-5.2 Pro
Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 52.3 on the Noometry Index.
Last verified . 8 shared benchmarks.
Summary
- They share 8 benchmarks with published results for both. Claude Opus 4.8 scores higher in 2 categories and GPT-5.2 Pro in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.8 leads 64.7 to 51.5.
- The biggest single-benchmark swing is ARC-AGI-2: 72.1% for Claude Opus 4.8 and 54.2% for GPT-5.2 Pro.
- Claude Opus 4.8 is cheaper at $5 / $25 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- Claude Opus 4.8 accepts more context: 1M tokens versus 400K.
Side by side
| Claude Opus 4.8 | GPT-5.2 Pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 60.7 | 52.3 |
| Released | 2026-05-28 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $5 | $21 |
| Output $ / M tokens | $25 | $168 |
| Results tracked | 65 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude Opus 4.8: 59.9 (#12), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4.8 | GPT-5.2 Pro |
|---|---|---|
| DeepSWE | 59% | — |
| FrontierCode | 46.5% | — |
| LMArena WebDev | 1556 | — |
| SciCode | 53.5% | — |
| GSO | 47.1% | — |
| WeirdML | 82.9% | — |
| LMArena Coding | 1490 | — |
| ALE-Bench | 1,564 | — |
Agentic & Tool Use Not comparable
Claude Opus 4.8: 47.6 (#11), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4.8 | GPT-5.2 Pro |
|---|---|---|
| APEX-Agents | 48.9% | — |
| OSWorld 2.0 | 20.6% | — |
| Remote Labor Index | 8.3% | — |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| GBAEval | 70.9% | — |
| GDP.pdf | 24% | — |
| LMArena Search | 1204 | — |
| Vending-Bench 2 | 5,787 | — |
Reasoning Claude Opus 4.8 leads
Claude Opus 4.8: 64.7 (#16), GPT-5.2 Pro: 51.5 (#33)
| Benchmark | Claude Opus 4.8 | GPT-5.2 Pro |
|---|---|---|
| ARC-AGI-2 | 72.1% | 54.2% |
| SimpleBench | 64.8% | 57.4% |
| NYT Connections (extended) | 91.1% | 79.3% |
| ARC-AGI-1 | 92.5% | 90.5% |
| Epoch Capabilities Index | 158.21 | 155.4 |
| Kagi LLM Benchmark | 88.8% | — |
| CritPt | 20.9% | — |
| Chess Puzzles | 34% | — |
| EnigmaEval | 23.5% | — |
| EBR-Bench | 28.6% | — |
| LMArena Hard Prompts | 1482 | — |
| Mystery Game Puzzles | 36% | — |
| DTBench | 94.9% | — |
| LMCA | 57.5% | — |
| Surface Evolver Bench | 87.5% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 59.9 | — |
Math Claude Opus 4.8 leads
Claude Opus 4.8: 78.4 (#13), GPT-5.2 Pro: 65.3 (#29)
| Benchmark | Claude Opus 4.8 | GPT-5.2 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 80% | 74% |
| FrontierMath Tier 4 | 56.1% | 46% |
| FrontierMath Tier 4 (v1) | 31.3% | 31.3% |
| MathArena Final-Answer Competitions | 91.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 69% | — |
| LMArena Math | 1487 | — |
| FrontierMath (Feb 2025 set) | 47.2% | — |
Knowledge Not comparable
Claude Opus 4.8: 61.3 (#29), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4.8 | GPT-5.2 Pro |
|---|---|---|
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 53% | — |
| LMArena Expert | 1502 | — |
Multimodal Not comparable
Claude Opus 4.8: 42.9 (#26), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4.8 | GPT-5.2 Pro |
|---|---|---|
| LMArena Vision | 1294 | — |
| Blueprint-Bench 2 | 14.5% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1475 | — |
Multilingual Not comparable
Claude Opus 4.8: 55.2 (#33), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4.8 | GPT-5.2 Pro |
|---|---|---|
| LMArena Non-English | 1450 | — |
| LMArena Chinese | 1507 | — |
| LMArena French | 1481 | — |
| LMArena German | 1472 | — |
| LMArena Japanese | 1440 | — |
| LMArena Korean | 1432 | — |
| LMArena Russian | 1474 | — |
| LMArena Spanish | 1466 | — |
Instruction Following Not comparable
Claude Opus 4.8: 77.4 (#24), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4.8 | GPT-5.2 Pro |
|---|---|---|
| LMArena Instruction Following | 1476 | — |
Long Context Not comparable
Claude Opus 4.8: 45.4 (#35), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4.8 | GPT-5.2 Pro |
|---|---|---|
| LMArena Longer Query | 1483 | — |
Writing & Preference Not comparable
Claude Opus 4.8: 72.0 (#16), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4.8 | GPT-5.2 Pro |
|---|---|---|
| LMArena Text | 1461 | — |
| LMArena Creative Writing | 1454 | — |
| EQ-Bench Creative Writing | 1840 | — |
| EQ-Bench 4 | 1281 | — |
| LMArena Multi-Turn | 1476 | — |
Frequently asked questions
Is Claude Opus 4.8 better than GPT-5.2 Pro?
Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 52.3 on the Noometry Index.
Which is cheaper, Claude Opus 4.8 or GPT-5.2 Pro?
Claude Opus 4.8 is cheaper. It lists at $5 per million input tokens and $25 per million output tokens; GPT-5.2 Pro lists at $21 and $168.
Which has the bigger context window?
Claude Opus 4.8 does, with 1M tokens against 400K.
How many benchmarks do Claude Opus 4.8 and GPT-5.2 Pro share?
8 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and GPT-5.2 Pro has 8.