Model comparison
DeepSeek-V3.1-Terminus vs Mercury 2
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 38.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeekSummary
- They share 12 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 6 categories and Mercury 2 in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V3.1-Terminus leads 41.5 to 33.2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.30 / $1 for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 128K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Mercury 2 | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 42.6 | 38.8 |
| Released | 2025-09-22 | 2026-02-20 |
| Weights | Open | Proprietary |
| Context window | 164K | 128K |
| Max output | 66K | 50K |
| Input $ / M tokens | $0.30 | $0.25 |
| Output $ / M tokens | $1 | $0.75 |
| Results tracked | 16 | 17 |
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: 41.5 (#114), Mercury 2: 33.2 (#250)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury 2 |
|---|---|---|
| SciCode | 40.6% | 38.7% |
| LMArena Coding | 1426 | 1391 |
| ALE-Bench | 745.17 | 785.58 |
| LMArena WebDev | — | 1170 |
| WeirdML | — | 43.2% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Mercury 2: 23.0 (#170)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury 2 |
|---|---|---|
| CritPt | 1.7% | 0.8% |
| LMArena Hard Prompts | 1427 | 1362 |
| Kagi LLM Benchmark | 57.4% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Not comparable
DeepSeek-V3.1-Terminus: 35.7 (#138), Mercury 2: —
| Benchmark | DeepSeek-V3.1-Terminus | Mercury 2 |
|---|---|---|
| LMArena Math | 1402 | — |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Mercury 2: 35.6 (#170)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | — | 12.3% |
| LMArena Expert | — | 1358 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Mercury 2: 46.8 (#153)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1407 | 1331 |
| LMArena Russian | 1434 | 1303 |
| LMArena Chinese | — | 1416 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Mercury 2: 70.4 (#161)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1328 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Mercury 2: 40.4 (#149)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1426 | 1329 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Mercury 2: 54.0 (#151)
| Benchmark | DeepSeek-V3.1-Terminus | Mercury 2 |
|---|---|---|
| LMArena Text | 1420 | 1355 |
| LMArena Creative Writing | 1404 | 1289 |
| LMArena Multi-Turn | 1411 | 1358 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Mercury 2?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 38.8 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.30 and $1.
Is DeepSeek-V3.1-Terminus or Mercury 2 better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 128K.
How many benchmarks do DeepSeek-V3.1-Terminus and Mercury 2 share?
12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Mercury 2 has 17.