Model comparison
DeepSeek-V2.5 (Sep 2024) vs Mercury 2.5
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 33.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in math, where DeepSeek-V2.5 (Sep 2024) leads 35.9 to 23.3.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Mercury 2.5 | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 37.6 | 33.5 |
| Released | 2024-09-06 | 2026-09-08 |
| Weights | Open | Proprietary |
| Context window | — | 260K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 22 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2.5 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Mercury 2.5: 39.5 (#156)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury 2.5 |
|---|---|---|
| Aider Polyglot | 17.8% | — |
| SciCode | — | 38.5% |
| BigCodeBench Instruct | 48.6% | — |
| LMArena Coding | 1309 | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 301.65 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Mercury 2.5: 22.4 (#193)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury 2.5 |
|---|---|---|
| CritPt | — | 0% |
| LMArena Hard Prompts | 1289 | — |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Mercury 2.5: 23.3 (#272)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury 2.5 |
|---|---|---|
| ProofBench | — | 3% |
| LMArena Math | 1288 | — |
Knowledge Not comparable
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Mercury 2.5: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury 2.5 |
|---|---|---|
| LMArena Expert | 1266 | — |
Multilingual Not comparable
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Mercury 2.5: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury 2.5 |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena Chinese | 1318 | — |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Not comparable
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Mercury 2.5: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury 2.5 |
|---|---|---|
| LMArena Instruction Following | 1280 | — |
Long Context Not comparable
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Mercury 2.5: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury 2.5 |
|---|---|---|
| LMArena Longer Query | 1301 | — |
Writing & Preference Not comparable
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Mercury 2.5: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury 2.5 |
|---|---|---|
| LMArena Text | 1294 | — |
| LMArena Creative Writing | 1285 | — |
| LMArena Multi-Turn | 1297 | — |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Mercury 2.5?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 33.5 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Mercury 2.5 better for coding?
Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Mercury 2.5 share?
0 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Mercury 2.5 has 4.