Model comparison
GPT-4 vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 29.1 on the Noometry Index.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen2.5 Plus 1127 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5 Plus 1127 leads 36.1 to 10.8.
Side by side
| GPT-4 | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 29.1 | 38.8 |
| Released | 2023-03-14 | — |
| Weights | Proprietary | Proprietary |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $60 | — |
| Results tracked | 38 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 Plus 1127 leads
GPT-4: 31.6 (#283), Qwen2.5 Plus 1127: 38.5 (#175)
| Benchmark | GPT-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1254 | 1314 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Qwen2.5 Plus 1127: —
| Benchmark | GPT-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning Qwen2.5 Plus 1127 leads
GPT-4: 17.8 (#289), Qwen2.5 Plus 1127: 25.9 (#141)
| Benchmark | GPT-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1299 |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Qwen2.5 Plus 1127 leads
GPT-4: 10.8 (#309), Qwen2.5 Plus 1127: 36.1 (#174)
| Benchmark | GPT-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1269 | 1298 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Qwen2.5 Plus 1127 leads
GPT-4: 18.4 (#282), Qwen2.5 Plus 1127: 35.5 (#183)
| Benchmark | GPT-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1211 | 1289 |
| GPQA Diamond | 35.7% | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual Qwen2.5 Plus 1127 leads
GPT-4: 40.6 (#215), Qwen2.5 Plus 1127: 41.9 (#201)
| Benchmark | GPT-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1246 | 1265 |
| LMArena Chinese | 1242 | 1314 |
| LMArena German | 1251 | 1231 |
| LMArena Japanese | 1209 | 1207 |
| LMArena Russian | 1251 | 1271 |
| LMArena French | 1283 | — |
| LMArena Korean | 1184 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Qwen2.5 Plus 1127 leads
GPT-4: 65.3 (#222), Qwen2.5 Plus 1127: 67.2 (#199)
| Benchmark | GPT-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1275 |
Long Context Qwen2.5 Plus 1127 leads
GPT-4: 37.7 (#212), Qwen2.5 Plus 1127: 39.2 (#184)
| Benchmark | GPT-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1244 | 1292 |
Writing & Preference Qwen2.5 Plus 1127 leads
GPT-4: 34.9 (#268), Qwen2.5 Plus 1127: 49.4 (#192)
| Benchmark | GPT-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1263 | 1299 |
| LMArena Creative Writing | 1244 | 1262 |
| LMArena Multi-Turn | 1257 | 1299 |
| EQ-Bench Creative Writing | 752 | — |
Frequently asked questions
Is GPT-4 better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 29.1 on the Noometry Index.
Is GPT-4 or Qwen2.5 Plus 1127 better for coding?
Qwen2.5 Plus 1127 scores higher on coding benchmarks: 38.5 versus 31.6 in the Noometry coding category.
How many benchmarks do GPT-4 and Qwen2.5 Plus 1127 share?
14 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen2.5 Plus 1127 has 14.