Model comparison
Deepseek Coder v2 vs Mercury
Mercury is the stronger model overall, scoring 37.6 to 35.9 on the Noometry Index.
Last verified . 8 shared benchmarks.
DeepSeekSummary
- They share 8 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Mercury in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury leads 46.2 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Mercury | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 35.9 | 37.6 |
| Released | 2024-06-17 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Deepseek Coder v2: 38.1 (#183), Mercury: 38.7 (#170)
| Benchmark | Deepseek Coder v2 | Mercury |
|---|---|---|
| LMArena Coding | 1251 | 1322 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Mercury: 17.5 (#293)
| Benchmark | Deepseek Coder v2 | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1285 |
| Kagi LLM Benchmark | — | 21.6% |
| WinoGrande | 83.7% | — |
Math Not comparable
Deepseek Coder v2: 34.9 (#190), Mercury: —
| Benchmark | Deepseek Coder v2 | Mercury |
|---|---|---|
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |
Knowledge Not comparable
Deepseek Coder v2: 32.3 (#212), Mercury: —
| Benchmark | Deepseek Coder v2 | Mercury |
|---|---|---|
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Mercury leads
Deepseek Coder v2: 36.3 (#240), Mercury: 41.6 (#206)
| Benchmark | Deepseek Coder v2 | Mercury |
|---|---|---|
| LMArena Non-English | 1182 | 1260 |
| LMArena Chinese | 1201 | — |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Mercury leads
Deepseek Coder v2: 61.7 (#242), Mercury: 65.2 (#224)
| Benchmark | Deepseek Coder v2 | Mercury |
|---|---|---|
| LMArena Instruction Following | 1180 | 1239 |
Long Context Mercury leads
Deepseek Coder v2: 37.0 (#224), Mercury: 38.4 (#198)
| Benchmark | Deepseek Coder v2 | Mercury |
|---|---|---|
| LMArena Longer Query | 1219 | 1266 |
Writing & Preference Mercury leads
Deepseek Coder v2: 38.2 (#253), Mercury: 46.2 (#221)
| Benchmark | Deepseek Coder v2 | Mercury |
|---|---|---|
| LMArena Text | 1191 | 1282 |
| LMArena Creative Writing | 1120 | 1191 |
| LMArena Multi-Turn | 1177 | 1282 |
Frequently asked questions
Is Deepseek Coder v2 better than Mercury?
Mercury is the stronger model overall, scoring 37.6 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Mercury better for coding?
They score almost the same on coding (38.1 vs 38.7); test both on your own repository before choosing.
How many benchmarks do Deepseek Coder v2 and Mercury share?
8 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Mercury has 9.