Model comparison
DeepSeek LLM 67B vs Mercury
Mercury is the stronger model overall, scoring 37.6 to 24.9 on the Noometry Index.
Last verified . 8 shared benchmarks.
DeepSeekSummary
- They share 8 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Mercury in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury leads 46.2 to 31.6.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Mercury | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 24.9 | 37.6 |
| Released | 2023-11-29 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury leads
DeepSeek LLM 67B: 31.9 (#278), Mercury: 38.7 (#170)
| Benchmark | DeepSeek LLM 67B | Mercury |
|---|---|---|
| LMArena Coding | 1096 | 1322 |
Reasoning Too close to call
DeepSeek LLM 67B: 16.5 (#304), Mercury: 17.5 (#293)
| Benchmark | DeepSeek LLM 67B | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1285 |
| Kagi LLM Benchmark | — | 21.6% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Not comparable
DeepSeek LLM 67B: 8.7 (#324), Mercury: —
| Benchmark | DeepSeek LLM 67B | Mercury |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge Not comparable
DeepSeek LLM 67B: 7.0 (#313), Mercury: —
| Benchmark | DeepSeek LLM 67B | Mercury |
|---|---|---|
| GPQA Diamond | 24.6% | — |
Multilingual Mercury leads
DeepSeek LLM 67B: 29.4 (#267), Mercury: 41.6 (#206)
| Benchmark | DeepSeek LLM 67B | Mercury |
|---|---|---|
| LMArena Non-English | 1073 | 1260 |
| LMArena Chinese | 1132 | — |
Instruction Following Mercury leads
DeepSeek LLM 67B: 55.4 (#277), Mercury: 65.2 (#224)
| Benchmark | DeepSeek LLM 67B | Mercury |
|---|---|---|
| LMArena Instruction Following | 1079 | 1239 |
Long Context Mercury leads
DeepSeek LLM 67B: 33.1 (#265), Mercury: 38.4 (#198)
| Benchmark | DeepSeek LLM 67B | Mercury |
|---|---|---|
| LMArena Longer Query | 1092 | 1266 |
Writing & Preference Mercury leads
DeepSeek LLM 67B: 31.6 (#282), Mercury: 46.2 (#221)
| Benchmark | DeepSeek LLM 67B | Mercury |
|---|---|---|
| LMArena Text | 1105 | 1282 |
| LMArena Creative Writing | 1067 | 1191 |
| LMArena Multi-Turn | 1082 | 1282 |
Frequently asked questions
Is DeepSeek LLM 67B better than Mercury?
Mercury is the stronger model overall, scoring 37.6 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Mercury better for coding?
Mercury scores higher on coding benchmarks: 38.7 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Mercury share?
8 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Mercury has 9.