Agentic
Like-for-like- GLM-5
- 56.2
- MiniMax M2.7
- 57.0
- Weighted basis
- 1 vs 1 rows
- Reading
- MiniMax M2.7 leads
Model comparison
GLM-5 vs MiniMax M2.7
Updated August 1, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
20 confirmed releases in the last 30 daysSee provider release alerts
GLM-5 has the higher public score estimate, 65.24 versus 63.09, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
12 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Agentic work
Tool use, computer use, and multi-step task completion
MiniMax M2.7
MiniMax M2.7 leads on the same 1 weighted benchmark row.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
MiniMax M2.7
MiniMax M2.7 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
MiniMax M2.7
MiniMax M2.7 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. GLM-5 does not fit this workload in one request. MiniMax M2.7 does not fit this workload in one request. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
24 GLM-5 only
12 Shared
6 MiniMax M2.7 only
- Shared results
- 12
- GLM-5 only
- 24
- MiniMax M2.7 only
- 6
- Like-for-like categories
- 1 / 8
1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Coding
Directional only- GLM-5
- 66.3
- MiniMax M2.7
- 53.3
- Weighted basis
- 3 vs 2 rows
- Reading
- Directional only
Reasoning
Not comparable- GLM-5
- 60.8
- MiniMax M2.7
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- GLM-5
- 66.4
- MiniMax M2.7
- Not measured
- Weighted basis
- 4 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- GLM-5
- 56.3
- MiniMax M2.7
- Not measured
- Weighted basis
- 4 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-5
- 83.1
- MiniMax M2.7
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-5
- Not measured
- MiniMax M2.7
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- GLM-5
- 92.6
- MiniMax M2.7
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
| Category | GLM-5 | MiniMax M2.7 | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 56.2 | 57.0 | Like-for-like1 vs 1 rows | MiniMax M2.7 leads |
| Coding | 66.3 | 53.3 | Directional only3 vs 2 rows | Directional only |
| Reasoning | 60.8 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Knowledge | 66.4 | Not measured | Not comparable4 vs 0 rows | Not comparable |
| Math | 56.3 | Not measured | Not comparable4 vs 0 rows | Not comparable |
| Multilingual | 83.1 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Multimodal | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Instruction following | 92.6 | Not measured | Not comparable1 vs 0 rows | Not comparable |
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
SWE-Rebench
Coding
SWE-bench Pro
Coding
Terminal-Bench 2.0
Agentic
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- GLM-5
- $0.0026
- Fits in one request
- MiniMax M2.7
- $0.0009
- Fits in one request
MiniMax M2.7 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GLM-5
- $0.0596
- Fits in one request
- MiniMax M2.7
- $0.0186
- Fits in one request
MiniMax M2.7 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GLM-5
- $0.252
- Does not fit in one request
- Cached input priced at the published list-input rate
- MiniMax M2.7
- $0.078
- Does not fit in one request
- Cached input priced at the published list-input rate
GLM-5 does not fit this workload in one request. MiniMax M2.7 does not fit this workload in one request. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGLM-5MiniMax M2.7
Context window
Maximum documented context; output-token limits may be lower.
GLM-5
200K
MiniMax M2.7
200K
API model ID
GLM-5
Not sourced
MiniMax M2.7
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GLM-5
Not published
MiniMax M2.7
Not published
Documented inputs
GLM-5
Not sourced
MiniMax M2.7
Not sourced
Documented outputs
GLM-5
Not sourced
MiniMax M2.7
Not sourced
Provider availability
GLM-5
Not sourced
MiniMax M2.7
Not sourced
Reasoning profile
GLM-5
Non-Reasoning
MiniMax M2.7
Non-Reasoning
Weight access
GLM-5
Open Weight
MiniMax M2.7
Open Weight
License
GLM-5
Open Weight
MiniMax M2.7
Open Weight
Release date
GLM-5
2026-03-01
MiniMax M2.7
2026-03-18
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- GLM-5 has the higher public score estimate, 65.24 versus 63.09, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.0596 vs $0.0186. Cache-heavy agent loop: $0.252 vs $0.078.
- Context tradeoff
- Both models list 200K.
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence42 rows
Agentic
Terminal-Bench 2.0
GLM-556.2%SourceMiniMax M2.757%SourceMiniMax M2.7 leads this result
Claw-Eval
GLM-557.7%SourceMiniMax M2.748.7%SourceGLM-5 leads this result
QwenClawBench
GLM-554.1%SourceMiniMax M2.7—Not directly comparable
τ³-bench results
GLM-565.6%SourceMiniMax M2.7—Not directly comparable
DeepPlanning
GLM-514.6%SourceMiniMax M2.7—Not directly comparable
Toolathlon
GLM-538%SourceMiniMax M2.746.3%SourceMiniMax M2.7 leads this result
MCP Atlas
GLM-531.1%SourceMiniMax M2.7—Not directly comparable
MCP-Tasks
GLM-560.8%SourceMiniMax M2.7—Not directly comparable
WideResearch
GLM-569.8%SourceMiniMax M2.7—Not directly comparable
CyberGym
GLM-543.2%SourceMiniMax M2.7—Not directly comparable
Gert Labs
Shared sourceGLM-550.99%MiniMax M2.740.40%GLM-5 leads this result
MLE-Bench Lite
GLM-5—MiniMax M2.766.6%SourceNot directly comparable
MM-ClawBench
GLM-5—MiniMax M2.762.7%SourceNot directly comparable
Coding
SWE-bench Verified
GLM-577.8%SourceMiniMax M2.7—Not directly comparable
SWE-bench Verified*
Shared sourceGLM-572.8%MiniMax M2.775.4%MiniMax M2.7 leads this result
SWE-bench Pro
GLM-555.1%SourceMiniMax M2.756.2%SourceMiniMax M2.7 leads this result
SWE Multilingual
GLM-573.3%SourceMiniMax M2.776.5%SourceMiniMax M2.7 leads this result
SWE-Rebench
GLM-562.8%SourceMiniMax M2.751.9%SourceGLM-5 leads this result
React Native Evals
Shared sourceGLM-574.8%MiniMax M2.771.4%GLM-5 leads this result
Multi-SWE Bench
GLM-5—MiniMax M2.752.7%SourceNot directly comparable
VIBE-Pro
GLM-5—MiniMax M2.755.6%SourceNot directly comparable
NL2Repo
GLM-5—MiniMax M2.739.8%SourceNot directly comparable
Vibe Code Bench
GLM-5—MiniMax M2.727.04%SourceNot directly comparable
Reasoning
Knowledge
GPQA
GLM-586%SourceMiniMax M2.7—Not directly comparable
GPQA-D
Shared sourceGLM-586.0%MiniMax M2.787.0%MiniMax M2.7 leads this result
SuperGPQA
GLM-566.8%SourceMiniMax M2.7—Not directly comparable
MMLU-Pro
GLM-585.7%SourceMiniMax M2.7—Not directly comparable
MMLU-Pro (Arcee)
Shared sourceGLM-585.8%MiniMax M2.780.8%GLM-5 leads this result
HLE
GLM-550.4%SourceMiniMax M2.7—Not directly comparable
Math
AIME26
GLM-595.8%SourceMiniMax M2.7—Not directly comparable
AIME25 (Arcee)
Shared sourceGLM-593.3%MiniMax M2.780.0%GLM-5 leads this result
HMMT Feb 2025
GLM-597.5%SourceMiniMax M2.7—Not directly comparable
HMMT Nov 2025
GLM-596.9%SourceMiniMax M2.7—Not directly comparable
HMMT Feb 2026
GLM-586.4%SourceMiniMax M2.7—Not directly comparable
MMAnswerBench
GLM-582.5%SourceMiniMax M2.7—Not directly comparable
FrontierMath v2 (Tiers 1-3)
GLM-516.434%SourceMiniMax M2.7—Not directly comparable
FrontierMath v2 (Tier 4)
GLM-52.100%SourceMiniMax M2.7—Not directly comparable
Multilingual
Instruction following
IFEval
GLM-592.6%SourceMiniMax M2.7—Not directly comparable
Frequently asked questions
Which is better, GLM-5 or MiniMax M2.7?
GLM-5 has the higher public score estimate, 65.24 versus 63.09, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, GLM-5 or MiniMax M2.7?
The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, GLM-5 or MiniMax M2.7?
MiniMax M2.7 leads the like-for-like agentic tasks comparison across 1 shared weighted benchmark row.
Which costs less, GLM-5 or MiniMax M2.7?
For the stated presets, chat costs $0.0026 on GLM-5 and $0.0009 on MiniMax M2.7; repository review costs $0.0596 and $0.0186; the cache-heavy agent loop costs $0.252 and $0.078. GLM-5 does not fit this workload in one request. MiniMax M2.7 does not fit this workload in one request. GLM-5 has no published cached-input rate, so cached tokens use its listed input rate. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, GLM-5 or MiniMax M2.7?
Both models list the same context window, 200K.
Related comparisons
Last updated August 1, 2026
Watch GLM-5 vs MiniMax M2.7
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.