Model comparison
DeepSeek-V3.1 vs Mercury
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 37.6 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeekSummary
- They share 9 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 5 categories and Mercury in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 46.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 53.2% for DeepSeek-V3.1 and 21.6% for Mercury.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Mercury | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 42.8 | 37.6 |
| Released | 2025-08-21 | — |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Mercury: 38.7 (#170)
| Benchmark | DeepSeek-V3.1 | Mercury |
|---|---|---|
| LMArena Coding | 1417 | 1322 |
| WeirdML | 38.4% | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Mercury: 17.5 (#293)
| Benchmark | DeepSeek-V3.1 | Mercury |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 21.6% |
| LMArena Hard Prompts | 1417 | 1285 |
| SimpleBench | 40% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math Not comparable
DeepSeek-V3.1: 38.9 (#122), Mercury: —
| Benchmark | DeepSeek-V3.1 | Mercury |
|---|---|---|
| LMArena Math | 1420 | — |
Knowledge Not comparable
DeepSeek-V3.1: 43.7 (#90), Mercury: —
| Benchmark | DeepSeek-V3.1 | Mercury |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1405 | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Mercury: 41.6 (#206)
| Benchmark | DeepSeek-V3.1 | Mercury |
|---|---|---|
| LMArena Non-English | 1400 | 1260 |
| LMArena Chinese | 1469 | — |
| LMArena French | 1447 | — |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Russian | 1405 | — |
| LMArena Spanish | 1431 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Mercury: 65.2 (#224)
| Benchmark | DeepSeek-V3.1 | Mercury |
|---|---|---|
| LMArena Instruction Following | 1400 | 1239 |
Long Context Mercury leads
DeepSeek-V3.1: 36.3 (#232), Mercury: 38.4 (#198)
| Benchmark | DeepSeek-V3.1 | Mercury |
|---|---|---|
| LMArena Longer Query | 1422 | 1266 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Mercury: 46.2 (#221)
| Benchmark | DeepSeek-V3.1 | Mercury |
|---|---|---|
| LMArena Text | 1420 | 1282 |
| LMArena Creative Writing | 1401 | 1191 |
| LMArena Multi-Turn | 1408 | 1282 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Mercury?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 37.6 on the Noometry Index.
Is DeepSeek-V3.1 or Mercury better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 38.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Mercury share?
9 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Mercury has 9.