Model comparison
DeepSeek-V2.5 (Sep 2024) vs Mercury
DeepSeek-V2.5 (Sep 2024) and Mercury score almost the same on the Noometry Index (37.6 vs 37.6), so choose on price, context window or the category you care about most.
Last verified . 8 shared benchmarks.
DeepSeekSummary
- They share 8 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 5 categories and Mercury in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V2.5 (Sep 2024) leads 25.6 to 17.5.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Mercury | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 37.6 | 37.6 |
| Released | 2024-09-06 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Mercury: 38.7 (#170)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury |
|---|---|---|
| LMArena Coding | 1309 | 1322 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Mercury: 17.5 (#293)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1285 |
| Kagi LLM Benchmark | — | 21.6% |
Math Not comparable
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Mercury: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury |
|---|---|---|
| LMArena Math | 1288 | — |
Knowledge Not comparable
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Mercury: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury |
|---|---|---|
| LMArena Expert | 1266 | — |
Multilingual Too close to call
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Mercury: 41.6 (#206)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury |
|---|---|---|
| LMArena Non-English | 1273 | 1260 |
| LMArena Chinese | 1318 | — |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Mercury: 65.2 (#224)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury |
|---|---|---|
| LMArena Instruction Following | 1280 | 1239 |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Mercury: 38.4 (#198)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury |
|---|---|---|
| LMArena Longer Query | 1301 | 1266 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Mercury: 46.2 (#221)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mercury |
|---|---|---|
| LMArena Text | 1294 | 1282 |
| LMArena Creative Writing | 1285 | 1191 |
| LMArena Multi-Turn | 1297 | 1282 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Mercury?
DeepSeek-V2.5 (Sep 2024) and Mercury score almost the same on the Noometry Index (37.6 vs 37.6), so choose on price, context window or the category you care about most.
Is DeepSeek-V2.5 (Sep 2024) or Mercury better for coding?
Mercury scores higher on coding benchmarks: 38.7 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Mercury share?
8 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Mercury has 9.