Model comparison
GLM-5 vs MiniMax M2.7
Head-to-head evidence from 26 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: GLM-5 #15; MiniMax M2.7 unranked
BenchAlign evidence: GLM-5 supported; MiniMax M2.7 supported. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GLM-5 and MiniMax M2.7 share 26 comparable benchmark results. 2 of 8 categories are comparable. 24 results are unique to GLM-5; 11 to MiniMax M2.7.
Updated July 16, 2026- Shared results
- 26
- GLM-5 only
- 24
- MiniMax M2.7 only
- 11
- Comparable categories
- 2 / 8
Pick GLM-5 if you want the stronger benchmark profile. MiniMax M2.7 only becomes the better choice if agentic is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 26 shared benchmark results across 7 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
GLM-5 is clearly ahead on the provisional aggregate, 63 to 52. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GLM-5's sharpest advantage is in coding, where it averages 66.3 against 53.3. The single biggest benchmark swing on the page is SWE-Rebench, 62.8% to 51.9%. MiniMax M2.7 does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
GLM-5 is also the more expensive model on tokens at $1.00 input / $3.20 output per 1M tokens, versus $0.30 input / $1.20 output per 1M tokens for MiniMax M2.7. That is roughly 2.7x on output cost alone.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | GLM-5 | Δ | MiniMax M2.7 |
|---|---|---|---|
| Coding | GLM-566.3 | Margin← 13.0 | MiniMax M2.753.3 |
| Agentic | GLM-556.2 | Margin→ 0.8 | MiniMax M2.757.0 |
| Reasoning | GLM-560.8 | MarginNo overlap | MiniMax M2.7Not measured |
| Knowledge | GLM-566.6 | MarginNo overlap | MiniMax M2.7Not measured |
| Math | GLM-556.3 | MarginNo overlap | MiniMax M2.7Not measured |
| Multilingual | GLM-583.1 | MarginNo overlap | MiniMax M2.7Not measured |
| Inst. Following | GLM-592.6 | MarginNo overlap | MiniMax M2.7Not measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-Rebench
CodingA 62.8%B 51.9%Winner: GLM-5Δ 10.9SWE-Rebench: GLM-5 scored 62.8%; MiniMax M2.7 scored 51.9%. GLM-5 wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 55.1%B 56.2%Winner: MiniMax M2.7Δ 1.1SWE-bench Pro: GLM-5 scored 55.1%; MiniMax M2.7 scored 56.2%. MiniMax M2.7 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 56.2%B 57%Winner: MiniMax M2.7Δ 0.8Terminal-Bench 2.0: GLM-5 scored 56.2%; MiniMax M2.7 scored 57%. MiniMax M2.7 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GLM-5 | MiniMax M2.7 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GLM-5$1 input / $3.2 output | MiniMax M2.7$0.3 input / $1.2 output | MiniMax M2.7 has the lower combined listed price. |
| Generation speedtokens per second | GLM-574 tok/s | MiniMax M2.745 tok/s | GLM-5 has the higher measured throughput. |
| First-answer latencyseconds to first token | GLM-51.64 s | MiniMax M2.72.53 s | GLM-5 reaches the first token sooner. |
| Context windowmaximum listed tokens | GLM-5200K | MiniMax M2.7200K | Listed context windows are equal. |
Benchmark Deep Dive
AgenticMiniMax M2.7 wins18 benchmarks
| Benchmark | GLM-5 | MiniMax M2.7 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 56.2% | 57% | MiniMax M2.7 leads |
| Claw-EvalSource | 57.7% | 48.7% | GLM-5 leads |
| QwenClawBenchSource | 54.1% | — | Not comparable |
| τ³-bench resultsSource | 65.6% | — | Not comparable |
| DeepPlanningSource | 14.6% | — | Not comparable |
| ToolathlonSource | 38% | 46.3% | MiniMax M2.7 leads |
| MCP AtlasSource | 31.1% | — | Not comparable |
| MCP-TasksSource | 60.8% | — | Not comparable |
| WideResearchSource | 69.8% | — | Not comparable |
| τ²-bench resultsSource | 98.2% | 84.8% | GLM-5 leads |
| CyberGymSource | 43.2% | — | Not comparable |
| APEX-Agents-AASource | 14.5% | 10.6% | GLM-5 leads |
| Gert LabsSource | 50.99% | 40.40% | GLM-5 leads |
| MLE-Bench LiteSource | — | 66.6% | Not comparable |
| MM-ClawBenchSource | — | 62.7% | Not comparable |
| AA Agentic IndexSource | — | 25.6% | Not comparable |
| GDPval-AASource | — | 32.9% | Not comparable |
| GDPval-AASource | — | 1158 | Not comparable |
CodingGLM-5 wins13 benchmarks
| Benchmark | GLM-5 | MiniMax M2.7 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 77.8% | — | Not comparable |
| SWE-bench Verified*Source | 72.8% | 75.4% | MiniMax M2.7 leads |
| SWE-bench ProSource | 55.1% | 56.2% | MiniMax M2.7 leads |
| SWE MultilingualSource | 73.3% | 76.5% | MiniMax M2.7 leads |
| SWE-RebenchSource | 62.8% | 51.9% | GLM-5 leads |
| React Native EvalsSource | 74.8% | 71.4% | GLM-5 leads |
| Terminal-Bench HardSource | 43.2% | 39.4% | GLM-5 leads |
| AA-SciCodeSource | 46.2% | 47.0% | MiniMax M2.7 leads |
| Multi-SWE BenchSource | — | 52.7% | Not comparable |
| VIBE-ProSource | — | 55.6% | Not comparable |
| NL2RepoSource | — | 39.8% | Not comparable |
| Vibe Code BenchSource | — | 27.04% | Not comparable |
| AA Coding IndexSource | — | 52.6% | Not comparable |
Reasoning4 benchmarks
Knowledge12 benchmarks
| Benchmark | GLM-5 | MiniMax M2.7 | Result |
|---|---|---|---|
| GPQASource | 86% | — | Not comparable |
| GPQA-DSource | 86.0% | 87.0% | MiniMax M2.7 leads |
| SuperGPQASource | 66.8% | — | Not comparable |
| MMLU-ProSource | 85.7% | — | Not comparable |
| MMLU-Pro (Arcee)Source | 85.8% | 80.8% | GLM-5 leads |
| HLESource | 50.4% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 39.5% | 38.1% | GLM-5 leads |
| AA-GPQA DiamondSource | 82.0% | 87.4% | MiniMax M2.7 leads |
| AA-HLESource | 27.2% | 28.1% | MiniMax M2.7 leads |
| AA-Omniscience IndexSource | 2.0% | 0.7% | GLM-5 leads |
| AA-Omniscience AccuracySource | 26.9% | 26.1% | GLM-5 leads |
| AA-Omniscience Hallucination RateSource | 34.0% | 34.4% | GLM-5 leads |
Math8 benchmarks
| Benchmark | GLM-5 | MiniMax M2.7 | Result |
|---|---|---|---|
| AIME26Source | 95.8% | — | Not comparable |
| AIME25 (Arcee)Source | 93.3% | 80.0% | GLM-5 leads |
| HMMT Feb 2025Source | 97.5% | — | Not comparable |
| HMMT Nov 2025Source | 96.9% | — | Not comparable |
| HMMT Feb 2026Source | 86.4% | — | Not comparable |
| MMAnswerBenchSource | 82.5% | — | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | 16.434% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 2.100% | — | Not comparable |
Multilingual2 benchmarks
Multimodal2 benchmarks
Frequently Asked Questions (3)
Which is better, GLM-5 or MiniMax M2.7?
GLM-5 is ahead on BenchLM's provisional leaderboard, 63 to 52. The biggest single separator in this matchup is SWE-Rebench, where the scores are 62.8% and 51.9%.
Which is better for coding, GLM-5 or MiniMax M2.7?
GLM-5 has the edge for coding in this comparison, averaging 66.3 versus 53.3. Inside this category, SWE-Rebench is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GLM-5 or MiniMax M2.7?
MiniMax M2.7 has the edge for agentic tasks in this comparison, averaging 57 versus 56.2. Inside this category, τ²-bench results is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.