Model comparison
Chatgpt 4o Latest 20250326 vs MiniMax-M2.5
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 38.3 on the Noometry Index.
Last verified . 19 shared benchmarks.
MiniMaxSummary
- They share 19 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 6 categories and MiniMax-M2.5 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Chatgpt 4o Latest 20250326 leads 33.8 to 17.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for Chatgpt 4o Latest 20250326 and 55.2% for MiniMax-M2.5.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| Chatgpt 4o Latest 20250326 | MiniMax-M2.5 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 43.8 | 38.3 |
| Released | — | 2026-02-12 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 21 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Chatgpt 4o Latest 20250326: 41.6 (#122), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Chatgpt 4o Latest 20250326 | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1413 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use Not comparable
Chatgpt 4o Latest 20250326: —, MiniMax-M2.5: 30.4 (#77)
| Benchmark | Chatgpt 4o Latest 20250326 | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |
Reasoning Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 33.8 (#71), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Chatgpt 4o Latest 20250326 | MiniMax-M2.5 |
|---|---|---|
| Kagi LLM Benchmark | 75% | 55.2% |
| LMArena Hard Prompts | 1424 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| Epoch Capabilities Index | — | 146.68 |
Math Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 38.6 (#134), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Chatgpt 4o Latest 20250326 | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1407 | 1378 |
| ProofBench | — | 4% |
Knowledge Too close to call
Chatgpt 4o Latest 20250326: 39.2 (#137), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Chatgpt 4o Latest 20250326 | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1401 | 1379 |
| Confabulations | 16.6% | — |
| Vectara Hallucination Rate | — | 9.1% |
Multimodal Not comparable
Chatgpt 4o Latest 20250326: 39.6 (#58), MiniMax-M2.5: —
| Benchmark | Chatgpt 4o Latest 20250326 | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 1243 | — |
Multilingual Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 52.9 (#76), MiniMax-M2.5: 47.1 (#152)
| Benchmark | Chatgpt 4o Latest 20250326 | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1419 | 1338 |
| LMArena Chinese | 1457 | 1393 |
| LMArena French | 1446 | 1362 |
| LMArena German | 1423 | 1362 |
| LMArena Japanese | 1405 | 1171 |
| LMArena Korean | 1396 | 1232 |
| LMArena Russian | 1429 | 1358 |
| LMArena Spanish | 1434 | 1354 |
Instruction Following Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 74.0 (#107), MiniMax-M2.5: 71.5 (#148)
| Benchmark | Chatgpt 4o Latest 20250326 | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1353 |
Long Context Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 43.1 (#107), MiniMax-M2.5: 37.5 (#216)
| Benchmark | Chatgpt 4o Latest 20250326 | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1413 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 62.6 (#72), MiniMax-M2.5: 53.9 (#153)
| Benchmark | Chatgpt 4o Latest 20250326 | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1429 | 1359 |
| LMArena Creative Writing | 1405 | 1331 |
| EQ-Bench Creative Writing | 1501 | 1361 |
| LMArena Multi-Turn | 1454 | 1364 |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than MiniMax-M2.5?
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 38.3 on the Noometry Index.
Is Chatgpt 4o Latest 20250326 or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 41.6 in the Noometry coding category.
How many benchmarks do Chatgpt 4o Latest 20250326 and MiniMax-M2.5 share?
19 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and MiniMax-M2.5 has 33.