Model comparison
Mercury vs Qwen-14B
Mercury is the stronger model overall, scoring 37.6 to 31.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Mercury scores higher in 5 categories and Qwen-14B in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury leads 46.2 to 27.6.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Mercury | Qwen-14B | |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 37.6 | 31.4 |
| Released | — | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury leads
Mercury: 38.7 (#170), Qwen-14B: 31.2 (#288)
| Benchmark | Mercury | Qwen-14B |
|---|---|---|
| LMArena Coding | 1322 | 1071 |
Reasoning Qwen-14B leads
Mercury: 17.5 (#293), Qwen-14B: 19.6 (#257)
| Benchmark | Mercury | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1285 | 1027 |
| Kagi LLM Benchmark | 21.6% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Not comparable
Mercury: —, Qwen-14B: 31.2 (#227)
| Benchmark | Mercury | Qwen-14B |
|---|---|---|
| LMArena Math | — | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Mercury: —, Qwen-14B: —
| Benchmark | Mercury | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Mercury leads
Mercury: 41.6 (#206), Qwen-14B: 27.5 (#275)
| Benchmark | Mercury | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1260 | 1041 |
| LMArena Chinese | — | 1077 |
Instruction Following Mercury leads
Mercury: 65.2 (#224), Qwen-14B: 52.4 (#289)
| Benchmark | Mercury | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1239 | 1031 |
Long Context Mercury leads
Mercury: 38.4 (#198), Qwen-14B: 31.3 (#280)
| Benchmark | Mercury | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1266 | 1028 |
Writing & Preference Mercury leads
Mercury: 46.2 (#221), Qwen-14B: 27.6 (#299)
| Benchmark | Mercury | Qwen-14B |
|---|---|---|
| LMArena Text | 1282 | 1051 |
| LMArena Creative Writing | 1191 | 1028 |
| LMArena Multi-Turn | 1282 | 1022 |
Frequently asked questions
Is Mercury better than Qwen-14B?
Mercury is the stronger model overall, scoring 37.6 to 31.4 on the Noometry Index.
Is Mercury or Qwen-14B better for coding?
Mercury scores higher on coding benchmarks: 38.7 versus 31.2 in the Noometry coding category.
How many benchmarks do Mercury and Qwen-14B share?
8 benchmarks have published results for both models. Mercury has 9 scored results on Noometry and Qwen-14B has 18.