Model comparison
DeepSeek-V2.5 (Sep 2024) vs MiniMax-M2
DeepSeek-V2.5 (Sep 2024) and MiniMax-M2 score almost the same on the Noometry Index (37.6 vs 37.4), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
DeepSeek
MiniMaxSummary
- They share 15 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and MiniMax-M2 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2 leads 39.3 to 31.7.
Side by side
| DeepSeek-V2.5 (Sep 2024) | MiniMax-M2 | |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 37.6 | 37.4 |
| Released | 2024-09-06 | 2025-10-27 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 22 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), MiniMax-M2: 39.3 (#159)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1309 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1297 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, MiniMax-M2: 25.1 (#109)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), MiniMax-M2: 19.4 (#258)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
Math MiniMax-M2 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), MiniMax-M2: 37.3 (#160)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1288 | 1352 |
Knowledge MiniMax-M2 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), MiniMax-M2: 37.0 (#163)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1266 | 1337 |
Multilingual MiniMax-M2 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), MiniMax-M2: 45.3 (#171)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1273 | 1313 |
| LMArena Chinese | 1318 | 1366 |
| LMArena French | 1289 | 1335 |
| LMArena German | 1258 | 1355 |
| LMArena Russian | 1289 | 1331 |
| LMArena Spanish | 1248 | 1326 |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
Instruction Following MiniMax-M2 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), MiniMax-M2: 70.2 (#166)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1328 |
Long Context Too close to call
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), MiniMax-M2: 40.5 (#153)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1301 | 1331 |
Writing & Preference MiniMax-M2 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), MiniMax-M2: 53.0 (#162)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1294 | 1340 |
| LMArena Creative Writing | 1285 | 1286 |
| LMArena Multi-Turn | 1297 | 1361 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than MiniMax-M2?
DeepSeek-V2.5 (Sep 2024) and MiniMax-M2 score almost the same on the Noometry Index (37.6 vs 37.4), so choose on price, context window or the category you care about most.
Is DeepSeek-V2.5 (Sep 2024) or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and MiniMax-M2 share?
15 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and MiniMax-M2 has 21.