Model comparison
DeepSeek-R1-Distill-Qwen-1.5B vs GPT-5.5 Instant
GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 26.1 on the Noometry Index.
Last verified . 3 shared benchmarks.
DeepSeekSummary
- They share 3 benchmarks with published results for both. DeepSeek-R1-Distill-Qwen-1.5B scores higher in 0 categories and GPT-5.5 Instant in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.5 Instant leads 48.9 to 16.0.
- The biggest single-benchmark swing is GPQA Diamond: 33.6% for DeepSeek-R1-Distill-Qwen-1.5B and 82.5% for GPT-5.5 Instant.
- DeepSeek-R1-Distill-Qwen-1.5B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1-Distill-Qwen-1.5B | GPT-5.5 Instant | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 26.1 | 42.7 |
| Released | 2025-01-20 | 2026-05-05 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 5 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.5 Instant leads
DeepSeek-R1-Distill-Qwen-1.5B: 21.8 (#336), GPT-5.5 Instant: 44.3 (#74)
| Benchmark | DeepSeek-R1-Distill-Qwen-1.5B | GPT-5.5 Instant |
|---|---|---|
| SciCode | — | 48.6% |
| BigCodeBench Instruct | 7% | — |
| LMArena Coding | — | 1433 |
| BigCodeBench Complete | 7.9% | — |
Reasoning GPT-5.5 Instant leads
DeepSeek-R1-Distill-Qwen-1.5B: 19.2 (#262), GPT-5.5 Instant: 24.9 (#155)
| Benchmark | DeepSeek-R1-Distill-Qwen-1.5B | GPT-5.5 Instant |
|---|---|---|
| Chess Puzzles | 0% | 12% |
| CritPt | — | 0% |
| LMArena Hard Prompts | — | 1426 |
| Epoch Capabilities Index | — | 142.52 |
Math GPT-5.5 Instant leads
DeepSeek-R1-Distill-Qwen-1.5B: 23.0 (#274), GPT-5.5 Instant: 26.5 (#259)
| Benchmark | DeepSeek-R1-Distill-Qwen-1.5B | GPT-5.5 Instant |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 21.4% | 68.1% |
| FrontierMath (Tiers 1-3) | — | 26.3% |
| FrontierMath Tier 4 | — | 2.4% |
| LMArena Math | — | 1420 |
Knowledge GPT-5.5 Instant leads
DeepSeek-R1-Distill-Qwen-1.5B: 16.0 (#290), GPT-5.5 Instant: 48.9 (#74)
| Benchmark | DeepSeek-R1-Distill-Qwen-1.5B | GPT-5.5 Instant |
|---|---|---|
| GPQA Diamond | 33.6% | 82.5% |
| LMArena Expert | — | 1409 |
Multimodal Not comparable
DeepSeek-R1-Distill-Qwen-1.5B: —, GPT-5.5 Instant: 40.0 (#52)
| Benchmark | DeepSeek-R1-Distill-Qwen-1.5B | GPT-5.5 Instant |
|---|---|---|
| LMArena Vision | — | 1250 |
| LMArena Document | — | 1403 |
Multilingual Not comparable
DeepSeek-R1-Distill-Qwen-1.5B: —, GPT-5.5 Instant: 52.8 (#80)
| Benchmark | DeepSeek-R1-Distill-Qwen-1.5B | GPT-5.5 Instant |
|---|---|---|
| LMArena Non-English | — | 1417 |
| LMArena Chinese | — | 1456 |
| LMArena French | — | 1428 |
| LMArena German | — | 1411 |
| LMArena Japanese | — | 1408 |
| LMArena Korean | — | 1392 |
| LMArena Russian | — | 1431 |
| LMArena Spanish | — | 1429 |
Instruction Following Not comparable
DeepSeek-R1-Distill-Qwen-1.5B: —, GPT-5.5 Instant: 74.2 (#100)
| Benchmark | DeepSeek-R1-Distill-Qwen-1.5B | GPT-5.5 Instant |
|---|---|---|
| LMArena Instruction Following | — | 1406 |
Long Context Not comparable
DeepSeek-R1-Distill-Qwen-1.5B: —, GPT-5.5 Instant: 43.4 (#96)
| Benchmark | DeepSeek-R1-Distill-Qwen-1.5B | GPT-5.5 Instant |
|---|---|---|
| LMArena Longer Query | — | 1422 |
Writing & Preference Not comparable
DeepSeek-R1-Distill-Qwen-1.5B: —, GPT-5.5 Instant: 61.8 (#85)
| Benchmark | DeepSeek-R1-Distill-Qwen-1.5B | GPT-5.5 Instant |
|---|---|---|
| LMArena Text | — | 1419 |
| LMArena Creative Writing | — | 1419 |
| LMArena Multi-Turn | — | 1433 |
Frequently asked questions
Is DeepSeek-R1-Distill-Qwen-1.5B better than GPT-5.5 Instant?
GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 26.1 on the Noometry Index.
Is DeepSeek-R1-Distill-Qwen-1.5B or GPT-5.5 Instant better for coding?
GPT-5.5 Instant scores higher on coding benchmarks: 44.3 versus 21.8 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Qwen-1.5B and GPT-5.5 Instant share?
3 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-1.5B has 5 scored results on Noometry and GPT-5.5 Instant has 27.