Model comparison
GPT-5.5 Instant vs Qwen2.5 72B Instruct
GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 31.9 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. GPT-5.5 Instant scores higher in 8 categories and Qwen2.5 72B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.5 Instant leads 48.9 to 27.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 68.1% for GPT-5.5 Instant and 8.1% for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.5 Instant | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.7 | 31.9 |
| Released | 2026-05-05 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 27 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.5 Instant leads
GPT-5.5 Instant: 44.3 (#74), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | GPT-5.5 Instant | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1433 | 1292 |
| SciCode | 48.6% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
GPT-5.5 Instant: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | GPT-5.5 Instant | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning GPT-5.5 Instant leads
GPT-5.5 Instant: 24.9 (#155), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | GPT-5.5 Instant | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1271 |
| Epoch Capabilities Index | 142.52 | 129 |
| CritPt | 0% | — |
| Chess Puzzles | 12% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math GPT-5.5 Instant leads
GPT-5.5 Instant: 26.5 (#259), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | GPT-5.5 Instant | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.1% | 8.1% |
| LMArena Math | 1420 | 1283 |
| FrontierMath (Tiers 1-3) | 26.3% | — |
| FrontierMath Tier 4 | 2.4% | — |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge GPT-5.5 Instant leads
GPT-5.5 Instant: 48.9 (#74), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | GPT-5.5 Instant | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 82.5% | 49.1% |
| LMArena Expert | 1409 | 1245 |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
GPT-5.5 Instant: 40.0 (#52), Qwen2.5 72B Instruct: —
| Benchmark | GPT-5.5 Instant | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1250 | — |
| LMArena Document | 1403 | — |
Multilingual GPT-5.5 Instant leads
GPT-5.5 Instant: 52.8 (#80), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | GPT-5.5 Instant | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1417 | 1252 |
| LMArena Chinese | 1456 | 1272 |
| LMArena French | 1428 | 1280 |
| LMArena German | 1411 | 1234 |
| LMArena Japanese | 1408 | 1180 |
| LMArena Korean | 1392 | 1188 |
| LMArena Russian | 1431 | 1264 |
| LMArena Spanish | 1429 | 1256 |
Instruction Following GPT-5.5 Instant leads
GPT-5.5 Instant: 74.2 (#100), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | GPT-5.5 Instant | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1406 | 1254 |
| IFEval | — | 80.6% |
Long Context GPT-5.5 Instant leads
GPT-5.5 Instant: 43.4 (#96), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | GPT-5.5 Instant | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1422 | 1282 |
Writing & Preference GPT-5.5 Instant leads
GPT-5.5 Instant: 61.8 (#85), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | GPT-5.5 Instant | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1419 | 1269 |
| LMArena Creative Writing | 1419 | 1221 |
| LMArena Multi-Turn | 1433 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is GPT-5.5 Instant better than Qwen2.5 72B Instruct?
GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 31.9 on the Noometry Index.
Is GPT-5.5 Instant or Qwen2.5 72B Instruct better for coding?
GPT-5.5 Instant scores higher on coding benchmarks: 44.3 versus 33.2 in the Noometry coding category.
How many benchmarks do GPT-5.5 Instant and Qwen2.5 72B Instruct share?
20 benchmarks have published results for both models. GPT-5.5 Instant has 27 scored results on Noometry and Qwen2.5 72B Instruct has 43.