Across 9 comparable benchmarks, MiniMax M2 has better reported results on 5 and worse on 4.
Strong evidence9 of 9 shared results countedHow we compare
Price basis: Listed rates vs listed rates. The price section below shows the applicable periods.
| Fact | MiniMax M2 | GLM-4.7-Flash |
|---|---|---|
| Context window | 205K tokens | 200K tokens |
| Input / 1M | $0.300 | $0.070 |
| Output / 1M | $1.20 | $0.400 |
| Blended (4:1) | $0.480 | $0.136 |
| Status | Available | Available |
| Released | October 27, 2025 | January 19, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 7 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
MiniMax M2 ahead on 2 of 2 counted
GLM-4.7-Flash ahead on 1 of 1 counted
MiniMax M2 ahead on 2 of 2 counted
MiniMax M2 ahead on 1 of 1 counted
GLM-4.7-Flash ahead on 2 of 2 counted
No shared comparable results for Abstract reasoning, Computer & tool use, Long context, Multimodal, Cybersecurity.
Published scores, with matching modes where available. Gaps show MiniMax M2 relative to GLM-4.7-Flash. Reading the results
| Benchmark | MiniMax M2 | GLM-4.7-Flash | Gap |
|---|---|---|---|
| SWE-bench VerifiedRepository Engineering · Accuracy | 69.4Thinking · tools | 59.2≠Thinking · no tools | +10.2 pts#63 vs #79 of 108 |
| Terminal Bench HardAgentic Development · Accuracy | 25.8Thinking · tools | 22.0Thinking · tools | +3.8 pts#78 vs #90 of 157 |
| AIME2025Mathematics · Accuracy | 78.0Thinking · no tools | 91.6Thinking · no tools | −13.6 pts#57 vs #33 of 86 |
| CritPtScientific Reasoning · Score | 0.9Thinking · no tools | 0.3Thinking · no tools | 3.00×#111 vs #124 of 134 |
| GPQA DiamondScientific Reasoning · Accuracy | 78.0Thinking · no tools | 75.2Thinking · no tools | +2.8 pts#116 vs #121 of 200 |
| BrowseCompFact Finding · Accuracy | 44.0Thinking · tools | 42.8Thinking · tools | +1.2 pts#52 vs #53 of 61 |
| τ²-BenchService Workflows · Accuracy | 77.2Thinking · tools | 79.5Thinking · tools | −2.3 pts#19 vs #16 of 40 |
| τ²-Bench - TelecomService Workflows · Accuracy | 87.0Thinking · tools | 98.8Thinking · tools | −11.8 pts#24 vs #4 of 34 |
| HLEKnowledge Exams · Accuracy | 12.5Thinking · no tools | 14.4Thinking · no tools | −1.9 pts#120 vs #117 of 151 |
Repository Engineering · Accuracy
Agentic Development · Accuracy
Mathematics · Accuracy
Scientific Reasoning · Score
Scientific Reasoning · Accuracy
Fact Finding · Accuracy
Service Workflows · Accuracy
Service Workflows · Accuracy
Knowledge Exams · Accuracy
A dash means no result is available.
| Benchmark | MiniMax M2 | GLM-4.7-Flash |
|---|---|---|
| MMLU-Pro | 82.0 | — |
| LiveCodeBench | 83.0 | — |
| Terminal-Bench 1.0 | 46.3 | — |
| Creative Writing | — | 1139 |
| SimpleBench | 25.0 | — |
| Vending-Bench 2 | 161 | — |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
MiniMax M2 costs253%morethan GLM-4.7-Flash per million tokens — 3.5× the price.Using listed rates vs listed rates at this token mix.
MiniMax M2: Listed text rates; pricing tier not confirmed.
GLM-4.7-Flash: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | MiniMax M2 | GLM-4.7-Flash | Ratio |
|---|---|---|---|
| Input | $0.30 | $0.07 | 4.29× |
| Output | $1.20 | $0.40 | 3.00× |
| Cached input | — | — | — |
| Cache write | — | — | — |
| Blended | $0.48 | $0.136 | 3.53× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Lower prices are highlighted. The cache hit rate applies to input tokens only; models without a published cached-input rate use their normal input price for those tokens.Effective dates: MiniMax M2 2026-11-14; GLM-4.7-Flash 2026-11-14.| Attribute | MiniMax M2 | GLM-4.7-Flash |
|---|---|---|
| Availability | Available | Available |
| Provider | MiniMaxAI | Zhipu AI |
| Model type | Chat model | Reasoning model |
| First release | October 27, 2025 | January 19, 2026 |
| Context window | 205K tokens | 200K tokens |
| Max output | — | 128K tokens |
| Total parameters | 230B | 31B |
| Active parameters | 10B | 3B |
| Architecture | Mixture of Experts (MoE) | Mixture of Experts (MoE) |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Multilingual |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
| Weights | Open weights | Open weights |
| Licence | MIT License | MIT License |
| Commercial use | Commercial use allowed | Commercial use allowed |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used MiniMax M2 or GLM-4.7-Flash? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.