Model comparison
GPT-5.2 vs GPT-5.5 Instant
GPT-5.2 is the stronger model overall, scoring 54.1 to 42.5 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. GPT-5.2 scores higher in 9 categories and GPT-5.5 Instant in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 leads 59.8 to 26.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 67.4% for GPT-5.2 and 26.3% for GPT-5.5 Instant.
Side by side
| GPT-5.2 | GPT-5.5 Instant | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 54.1 | 42.5 |
| Released | 2025-12-11 | 2026-05-05 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 67 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
GPT-5.2: 52.2 (#32), GPT-5.5 Instant: 43.7 (#73)
| Benchmark | GPT-5.2 | GPT-5.5 Instant |
|---|---|---|
| LMArena Coding | 1447 | 1433 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1415 | — |
| SWE-bench Multilingual | 66.7% | — |
| SciCode | — | 48.6% |
| GSO | 27.4% | — |
| WeirdML | 72.2% | — |
| ALE-Bench | 1,294 | — |
| AlgoTune | 2.05 | — |
Agentic & Tool Use Not comparable
GPT-5.2: 40.0 (#24), GPT-5.5 Instant: —
| Benchmark | GPT-5.2 | GPT-5.5 Instant |
|---|---|---|
| Terminal-Bench | 64.9% | — |
| Berkeley Function Calling Leaderboard | 55.9% | — |
| GDPval | 49.7% | — |
| Remote Labor Index | 2.5% | — |
| τ²-bench Airline | 83% | — |
| τ²-bench Banking | 32.2% | — |
| τ²-bench Retail | 81.6% | — |
| τ²-bench Telecom | 89.7% | — |
| DeepResearch Bench | 41.1% | — |
| LMArena Search | 1207 | — |
| METR Time Horizons | 75.3% | — |
| Vending-Bench 2 | 3,591 | — |
Reasoning GPT-5.2 leads
GPT-5.2: 50.1 (#33), GPT-5.5 Instant: 24.2 (#149)
| Benchmark | GPT-5.2 | GPT-5.5 Instant |
|---|---|---|
| Chess Puzzles | 49% | 12% |
| LMArena Hard Prompts | 1445 | 1426 |
| Epoch Capabilities Index | 153.45 | 142.48 |
| ARC-AGI-2 | 52.9% | — |
| SimpleBench | 45.8% | — |
| Kagi LLM Benchmark | 73.3% | — |
| NYT Connections (extended) | 83.6% | — |
| ARC-AGI-1 | 86.2% | — |
| CritPt | — | 0% |
| EnigmaEval | 10.4% | — |
| EBR-Bench | 23% | — |
| Mystery Game Puzzles | 23% | — |
| DTBench | 90.9% | — |
| LMCA | 43.9% | — |
| ForecastBench | 60.1 | — |
Math GPT-5.2 leads
GPT-5.2: 59.8 (#32), GPT-5.5 Instant: 26.1 (#241)
| Benchmark | GPT-5.2 | GPT-5.5 Instant |
|---|---|---|
| FrontierMath (Tiers 1-3) | 67.4% | 26.3% |
| FrontierMath Tier 4 | 31.7% | 2.4% |
| OTIS Mock AIME 2024-2025 | 96.1% | 68.1% |
| LMArena Math | 1439 | 1420 |
| MathArena Final-Answer Competitions | 72% | — |
| ProofBench | 15% | — |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Tier 4 (v1) | 18.8% | — |
Knowledge GPT-5.2 leads
GPT-5.2: 59.2 (#29), GPT-5.5 Instant: 48.9 (#68)
| Benchmark | GPT-5.2 | GPT-5.5 Instant |
|---|---|---|
| GPQA Diamond | 91.4% | 82.5% |
| LMArena Expert | 1445 | 1409 |
| Humanity's Last Exam | 27.8% | — |
| SimpleQA Verified | 37.1% | — |
| Vectara Hallucination Rate | 8.4% | — |
Multimodal GPT-5.2 leads
GPT-5.2: 50.9 (#7), GPT-5.5 Instant: 39.3 (#48)
| Benchmark | GPT-5.2 | GPT-5.5 Instant |
|---|---|---|
| LMArena Vision | 1268 | 1250 |
| LMArena Document | 1405 | 1403 |
| VPCT | 84% | — |
| Furniture Assembly | 38.3% | — |
Multilingual Too close to call
GPT-5.2: 53.6 (#63), GPT-5.5 Instant: 53.0 (#76)
| Benchmark | GPT-5.2 | GPT-5.5 Instant |
|---|---|---|
| LMArena Non-English | 1425 | 1417 |
| LMArena Chinese | 1460 | 1457 |
| LMArena French | 1456 | 1428 |
| LMArena German | 1448 | 1410 |
| LMArena Japanese | 1421 | 1408 |
| LMArena Korean | 1390 | 1393 |
| LMArena Russian | 1440 | 1430 |
| LMArena Spanish | 1433 | 1430 |
Instruction Following Too close to call
GPT-5.2: 74.9 (#83), GPT-5.5 Instant: 74.4 (#94)
| Benchmark | GPT-5.2 | GPT-5.5 Instant |
|---|---|---|
| LMArena Instruction Following | 1417 | 1407 |
Long Context Too close to call
GPT-5.2: 44.0 (#74), GPT-5.5 Instant: 43.4 (#92)
| Benchmark | GPT-5.2 | GPT-5.5 Instant |
|---|---|---|
| LMArena Longer Query | 1428 | 1422 |
| CL-bench | 18.2% | — |
Writing & Preference GPT-5.2 leads
GPT-5.2: 67.0 (#30), GPT-5.5 Instant: 62.0 (#81)
| Benchmark | GPT-5.2 | GPT-5.5 Instant |
|---|---|---|
| LMArena Text | 1439 | 1419 |
| LMArena Creative Writing | 1402 | 1420 |
| LMArena Multi-Turn | 1458 | 1434 |
| EQ-Bench Creative Writing | 1703 | — |
Frequently asked questions
Is GPT-5.2 better than GPT-5.5 Instant?
GPT-5.2 is the stronger model overall, scoring 54.1 to 42.5 on the Noometry Index.
Is GPT-5.2 or GPT-5.5 Instant better for coding?
GPT-5.2 scores higher on coding benchmarks: 52.2 versus 43.7 in the Noometry coding category.
How many benchmarks do GPT-5.2 and GPT-5.5 Instant share?
25 benchmarks have published results for both models. GPT-5.2 has 67 scored results on Noometry and GPT-5.5 Instant has 27.