Model comparison
DeepSeek-V3.1-Terminus vs Mercury
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 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-Terminus scores higher in 6 categories and Mercury in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 46.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 21.6% for Mercury.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Mercury | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 43.1 | 37.6 |
| Released | 2025-09-22 | — |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Mercury: 38.7 (#170)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury |
|---|---|---|
| LMArena Coding | 1426 | 1322 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Mercury: 17.5 (#293)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 21.6% |
| LMArena Hard Prompts | 1426 | 1285 |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Not comparable
DeepSeek-V3.1-Terminus: 38.5 (#137), Mercury: —
| Benchmark | DeepSeek-V3.1-Terminus | Mercury |
|---|---|---|
| LMArena Math | 1402 | — |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Mercury: 41.6 (#206)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury |
|---|---|---|
| LMArena Non-English | 1407 | 1260 |
| LMArena Russian | 1436 | — |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Mercury: 65.2 (#224)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury |
|---|---|---|
| LMArena Instruction Following | 1404 | 1239 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Mercury: 38.4 (#198)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury |
|---|---|---|
| LMArena Longer Query | 1421 | 1266 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Mercury: 46.2 (#221)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury |
|---|---|---|
| LMArena Text | 1419 | 1282 |
| LMArena Creative Writing | 1403 | 1191 |
| LMArena Multi-Turn | 1411 | 1282 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Mercury?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 37.6 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Mercury better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 38.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Mercury share?
9 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Mercury has 9.