Model comparison
DeepSeek-V2.5 (Sep 2024) vs MiniMax-M2.5
MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 37.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
MiniMaxSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 3 categories and MiniMax-M2.5 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 47.9 to 31.3.
Side by side
| DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.5 | |
|---|---|---|
| Provider | DeepSeek | MiniMax |
| Noometry Index | 37.0 | 38.1 |
| Released | 2024-09-06 | 2026-02-12 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 22 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), MiniMax-M2.5: 47.9 (#53)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1310 | 1380 |
| SWE-bench Verified (bash only) | — | 75.8% |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1386 |
| SWE-bench Multilingual | — | 68.3% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 618.17 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, MiniMax-M2.5: 30.2 (#70)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), MiniMax-M2.5: 17.6 (#281)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| Epoch Capabilities Index | — | 146.68 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), MiniMax-M2.5: 25.8 (#242)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1289 | 1378 |
| ProofBench | — | 4% |
Knowledge MiniMax-M2.5 leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), MiniMax-M2.5: 38.6 (#132)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1266 | 1378 |
| Vectara Hallucination Rate | — | 9.1% |
Multilingual MiniMax-M2.5 leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), MiniMax-M2.5: 47.3 (#147)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1273 | 1338 |
| LMArena Chinese | 1317 | 1392 |
| LMArena French | 1288 | 1363 |
| LMArena German | 1258 | 1361 |
| LMArena Japanese | 1228 | 1169 |
| LMArena Korean | 1209 | 1232 |
| LMArena Russian | 1289 | 1359 |
| LMArena Spanish | 1248 | 1354 |
Instruction Following MiniMax-M2.5 leads
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), MiniMax-M2.5: 71.7 (#143)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1353 |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), MiniMax-M2.5: 37.4 (#211)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1301 | 1367 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiniMax-M2.5 leads
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), MiniMax-M2.5: 54.1 (#149)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1294 | 1359 |
| LMArena Creative Writing | 1285 | 1331 |
| LMArena Multi-Turn | 1297 | 1364 |
| EQ-Bench Creative Writing | — | 1361 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than MiniMax-M2.5?
MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 37.0 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and MiniMax-M2.5 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and MiniMax-M2.5 has 33.