Model comparison
GPT-4 Turbo vs Qwen-14B
GPT-4 Turbo and Qwen-14B score almost the same on the Noometry Index (30.5 vs 31.4), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. GPT-4 Turbo scores higher in 5 categories and Qwen-14B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen-14B leads 31.2 to 9.0.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| GPT-4 Turbo | Qwen-14B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 30.5 | 31.4 |
| Released | 2023-11-06 | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $30 | — |
| Results tracked | 36 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4 Turbo leads
GPT-4 Turbo: 33.8 (#249), Qwen-14B: 31.2 (#288)
| Benchmark | GPT-4 Turbo | Qwen-14B |
|---|---|---|
| LMArena Coding | 1268 | 1071 |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Qwen-14B: —
| Benchmark | GPT-4 Turbo | Qwen-14B |
|---|---|---|
| METR Time Horizons | 36.7% | — |
Reasoning Qwen-14B leads
GPT-4 Turbo: 15.3 (#317), Qwen-14B: 19.6 (#257)
| Benchmark | GPT-4 Turbo | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1027 |
| Epoch Capabilities Index | 127.25 | 113.03 |
| SimpleBench | 25.1% | — |
| Chess Puzzles | 6% | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| BIG-Bench Hard | — | 55% |
| ForecastBench | 59.4 | — |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Qwen-14B leads
GPT-4 Turbo: 9.0 (#322), Qwen-14B: 31.2 (#227)
| Benchmark | GPT-4 Turbo | Qwen-14B |
|---|---|---|
| LMArena Math | 1272 | 1068 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| MATH Level 5 | 46.7% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
GPT-4 Turbo: 24.3 (#268), Qwen-14B: —
| Benchmark | GPT-4 Turbo | Qwen-14B |
|---|---|---|
| MMLU | 81.3% | 66.3% |
| GPQA Diamond | 46.6% | — |
| Confabulations | 28.4% | — |
| LMArena Expert | 1223 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
Multimodal Not comparable
GPT-4 Turbo: 30.6 (#110), Qwen-14B: —
| Benchmark | GPT-4 Turbo | Qwen-14B |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual GPT-4 Turbo leads
GPT-4 Turbo: 40.5 (#216), Qwen-14B: 27.5 (#275)
| Benchmark | GPT-4 Turbo | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1245 | 1041 |
| LMArena Chinese | 1242 | 1077 |
| LMArena French | 1276 | — |
| LMArena German | 1259 | — |
| LMArena Japanese | 1194 | — |
| LMArena Korean | 1187 | — |
| LMArena Russian | 1259 | — |
| LMArena Spanish | 1260 | — |
Instruction Following GPT-4 Turbo leads
GPT-4 Turbo: 65.8 (#216), Qwen-14B: 52.4 (#289)
| Benchmark | GPT-4 Turbo | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1249 | 1031 |
Long Context GPT-4 Turbo leads
GPT-4 Turbo: 38.0 (#206), Qwen-14B: 31.3 (#280)
| Benchmark | GPT-4 Turbo | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1254 | 1028 |
Writing & Preference GPT-4 Turbo leads
GPT-4 Turbo: 47.7 (#206), Qwen-14B: 27.6 (#299)
| Benchmark | GPT-4 Turbo | Qwen-14B |
|---|---|---|
| LMArena Text | 1272 | 1051 |
| LMArena Creative Writing | 1269 | 1028 |
| LMArena Multi-Turn | 1267 | 1022 |
Frequently asked questions
Is GPT-4 Turbo better than Qwen-14B?
GPT-4 Turbo and Qwen-14B score almost the same on the Noometry Index (30.5 vs 31.4), so choose on price, context window or the category you care about most.
Is GPT-4 Turbo or Qwen-14B better for coding?
GPT-4 Turbo scores higher on coding benchmarks: 33.8 versus 31.2 in the Noometry coding category.
How many benchmarks do GPT-4 Turbo and Qwen-14B share?
12 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Qwen-14B has 18.