Model comparison
DeepSeek-V2.5 (Sep 2024) vs MiniMax-M2.7
DeepSeek-V2.5 (Sep 2024) and MiniMax-M2.7 score almost the same on the Noometry Index (37.6 vs 37.7), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
DeepSeek
MiniMaxSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 2 categories and MiniMax-M2.7 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.7 leads 41.8 to 31.7.
Side by side
| DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.7 | |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 37.6 | 37.7 |
| Released | 2024-09-06 | 2026-03-18 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 22 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), MiniMax-M2.7: 41.8 (#120)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Coding | 1309 | 1454 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1398 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 599.25 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, MiniMax-M2.7: 25.1 (#111)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), MiniMax-M2.7: 19.7 (#253)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1422 |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| Epoch Capabilities Index | — | 145.85 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), MiniMax-M2.7: 25.9 (#263)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1288 | 1420 |
| ProofBench | — | 3% |
Knowledge MiniMax-M2.7 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), MiniMax-M2.7: 37.7 (#152)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1266 | 1444 |
| Vectara Hallucination Rate | — | 12.9% |
Multilingual MiniMax-M2.7 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), MiniMax-M2.7: 50.3 (#123)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1273 | 1382 |
| LMArena Chinese | 1318 | 1441 |
| LMArena French | 1289 | 1421 |
| LMArena German | 1258 | 1398 |
| LMArena Japanese | 1228 | 1262 |
| LMArena Korean | 1209 | 1313 |
| LMArena Russian | 1289 | 1383 |
| LMArena Spanish | 1248 | 1403 |
Instruction Following MiniMax-M2.7 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), MiniMax-M2.7: 74.1 (#103)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1405 |
Long Context MiniMax-M2.7 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), MiniMax-M2.7: 43.3 (#99)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1301 | 1419 |
Writing & Preference MiniMax-M2.7 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), MiniMax-M2.7: 58.9 (#112)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1294 | 1405 |
| LMArena Creative Writing | 1285 | 1354 |
| LMArena Multi-Turn | 1297 | 1412 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than MiniMax-M2.7?
DeepSeek-V2.5 (Sep 2024) and MiniMax-M2.7 score almost the same on the Noometry Index (37.6 vs 37.7), so choose on price, context window or the category you care about most.
Is DeepSeek-V2.5 (Sep 2024) or MiniMax-M2.7 better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and MiniMax-M2.7 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and MiniMax-M2.7 has 30.