Model comparison
GPT-5.6 Terra vs MiniMax-M2
GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 36.9 on the Noometry Index. MiniMax-M2 costs 8.6× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
MiniMaxSummary
- They share 19 benchmarks with published results for both. GPT-5.6 Terra scores higher in 9 categories and MiniMax-M2 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.5 to 34.6.
- The biggest single-benchmark swing is NYT Connections (extended): 78.4% for GPT-5.6 Terra and 14.8% for MiniMax-M2.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Terra | MiniMax-M2 | |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 59.1 | 36.9 |
| Released | 2026-07-09 | 2025-10-27 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 205K |
| Max output | 128K | 131K |
| Input $ / M tokens | $2 | $0.30 |
| Output $ / M tokens | $12 | $1.20 |
| Results tracked | 52 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
GPT-5.6 Terra: 57.1 (#16), MiniMax-M2: 39.1 (#151)
| Benchmark | GPT-5.6 Terra | MiniMax-M2 |
|---|---|---|
| LMArena WebDev | 1520 | 1297 |
| LMArena Coding | 1484 | 1370 |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| SWE-bench Verified (bash only) | — | 61% |
| CursorBench | 41.3% | — |
| SciCode | 55% | — |
| WeirdML | 78.3% | — |
| ALE-Bench | 1,951 | — |
Agentic & Tool Use GPT-5.6 Terra leads
GPT-5.6 Terra: 40.2 (#23), MiniMax-M2: 24.9 (#102)
| Benchmark | GPT-5.6 Terra | MiniMax-M2 |
|---|---|---|
| Vending-Bench 2 | 7,343 | 160.6 |
| Terminal-Bench | — | 30% |
| APEX-Agents | 58.2% | — |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
Reasoning GPT-5.6 Terra leads
GPT-5.6 Terra: 60.6 (#19), MiniMax-M2: 18.6 (#256)
| Benchmark | GPT-5.6 Terra | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 51.3% | 57.8% |
| NYT Connections (extended) | 78.4% | 14.8% |
| LMArena Hard Prompts | 1467 | 1357 |
| ARC-AGI-2 | 83.9% | — |
| SimpleBench | 48.9% | — |
| ARC-AGI-1 | 96.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 54% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 93.3% | — |
| LMCA | 55% | — |
| Surface Evolver Bench | 83.8% | — |
| Epoch Capabilities Index | 159.31 | — |
Math GPT-5.6 Terra leads
GPT-5.6 Terra: 81.5 (#10), MiniMax-M2: 34.6 (#158)
| Benchmark | GPT-5.6 Terra | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1463 | 1350 |
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| OTIS Mock AIME 2024-2025 | 99.7% | — |
| ProofBench | 74% | — |
Knowledge GPT-5.6 Terra leads
GPT-5.6 Terra: 61.3 (#27), MiniMax-M2: 36.3 (#160)
| Benchmark | GPT-5.6 Terra | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1492 | 1336 |
| GPQA Diamond | 93.3% | — |
| SimpleQA Verified | 43.2% | — |
Multimodal Not comparable
GPT-5.6 Terra: 47.5 (#10), MiniMax-M2: —
| Benchmark | GPT-5.6 Terra | MiniMax-M2 |
|---|---|---|
| LMArena Vision | 1271 | — |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |
Multilingual GPT-5.6 Terra leads
GPT-5.6 Terra: 54.5 (#42), MiniMax-M2: 45.6 (#165)
| Benchmark | GPT-5.6 Terra | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1439 | 1314 |
| LMArena Chinese | 1514 | 1367 |
| LMArena French | 1476 | 1336 |
| LMArena German | 1462 | 1366 |
| LMArena Russian | 1450 | 1332 |
| LMArena Spanish | 1455 | 1326 |
| LMArena Japanese | 1446 | — |
| LMArena Korean | 1420 | — |
Instruction Following GPT-5.6 Terra leads
GPT-5.6 Terra: 76.6 (#38), MiniMax-M2: 70.4 (#160)
| Benchmark | GPT-5.6 Terra | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1453 | 1329 |
Long Context GPT-5.6 Terra leads
GPT-5.6 Terra: 44.4 (#64), MiniMax-M2: 40.5 (#148)
| Benchmark | GPT-5.6 Terra | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1452 | 1332 |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.4 (#21), MiniMax-M2: 53.3 (#157)
| Benchmark | GPT-5.6 Terra | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1446 | 1340 |
| LMArena Creative Writing | 1411 | 1288 |
| LMArena Multi-Turn | 1451 | 1362 |
| EQ-Bench Creative Writing | 1855 | — |
| EQ-Bench 4 | 1234 | — |
Frequently asked questions
Is GPT-5.6 Terra better than MiniMax-M2?
GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 36.9 on the Noometry Index. MiniMax-M2 costs 8.6× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.
Which is cheaper, GPT-5.6 Terra or MiniMax-M2?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is GPT-5.6 Terra or MiniMax-M2 better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.1 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 205K.
How many benchmarks do GPT-5.6 Terra and MiniMax-M2 share?
19 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and MiniMax-M2 has 21.