Coding
Directional only- GLM-4.6
- 48.8
- Estimated · #84/183
- MiniMax M2.7
- 50.5
- Estimated · #70/183
- Basis
- BenchAlign lane · 1 vs 11 public rows
- Reading
- Directional only
GLM-4.6 vs MiniMax M2.7
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
MiniMax M2.7 has the higher public score estimate, 58.98 versus 53.94, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
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.
No workload recommendation clears the current evidence threshold.
Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
GLM-4.6 and MiniMax M2.7 are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GLM-4.6 is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
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-4.6 does not fit this workload in one request. MiniMax M2.7 does not fit this workload in one request. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate. GLM-4.6 has no comparable published API token rate.
Confidence: rate-fallback
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
2 GLM-4.6 only
1 Shared
22 MiniMax M2.7 only
- Shared results
- 1
- GLM-4.6 only
- 2
- MiniMax M2.7 only
- 22
- Like-for-like categories
- 0 / 8
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Knowledge
Directional only- GLM-4.6
- 45.3
- Estimated · #115/181
- MiniMax M2.7
- 50.2
- Supported · #88/181
- Basis
- BenchAlign lane · 0 vs 4 public rows
- Reading
- Directional only
Instruction following
Directional only- GLM-4.6
- 42.1
- #98/120
- MiniMax M2.7
- 92.7
- #10/120
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Agentic
Not comparable- GLM-4.6
- Not ranked
- MiniMax M2.7
- 43.1
- Estimated · #107/151
- Basis
- BenchAlign lane · 0 vs 7 public rows
- Reading
- Not comparable
Reasoning
Not comparable- GLM-4.6
- 41.4
- Unranked · 2 rankable rows
- MiniMax M2.7
- 75.2
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- GLM-4.6
- 27.5
- Unranked · 2 rankable rows
- MiniMax M2.7
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GLM-4.6
- Not ranked
- MiniMax M2.7
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GLM-4.6
- Not ranked
- MiniMax M2.7
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | GLM-4.6 | MiniMax M2.7 | Basis | Reading |
|---|---|---|---|---|
| Coding | 48.8Estimated · #84/183 | 50.5Estimated · #70/183 | Directional onlyBenchAlign lane · 1 vs 11 public rows | Directional only |
| Knowledge | 45.3Estimated · #115/181 | 50.2Supported · #88/181 | Directional onlyBenchAlign lane · 0 vs 4 public rows | Directional only |
| Instruction following | 42.1#98/120 | 92.7#10/120 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Agentic | Not ranked | 43.1Estimated · #107/151 | Not comparableBenchAlign lane · 0 vs 7 public rows | Not comparable |
| Reasoning | 41.4Unranked · 2 rankable rows | 75.2Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 27.5Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
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-4.6
- API rate not published
- Fits in one request
- MiniMax M2.7
- $0.0009
- Fits in one request
GLM-4.6 has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- GLM-4.6
- API rate not published
- Fits in one request
- MiniMax M2.7
- $0.0186
- Fits in one request
GLM-4.6 has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GLM-4.6
- API rate not published
- Does not fit in one request
- Cached-input rate unavailable
- MiniMax M2.7
- $0.078
- Does not fit in one request
- Cached input priced at the published list-input rate
GLM-4.6 does not fit this workload in one request. MiniMax M2.7 does not fit this workload in one request. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate. GLM-4.6 has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGLM-4.6MiniMax M2.7
Context window
Maximum documented context; output-token limits may be lower.
GLM-4.6
200K
MiniMax M2.7
200K
API model ID
GLM-4.6
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-4.6
No comparable hosted API rate
MiniMax M2.7
Not published
Documented inputs
GLM-4.6
Not sourced
MiniMax M2.7
Not sourced
Documented outputs
GLM-4.6
Not sourced
MiniMax M2.7
Not sourced
Provider availability
GLM-4.6
Not sourced
MiniMax M2.7
Not sourced
Reasoning profile
GLM-4.6
Reasoning
MiniMax M2.7
Non-Reasoning
Weight access
GLM-4.6
Open Weight
MiniMax M2.7
Open Weight
License
GLM-4.6
Open Weight
MiniMax M2.7
Open Weight
Release date
GLM-4.6
2025-09-01
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
- MiniMax M2.7 has the higher public score estimate, 58.98 versus 53.94, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- 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 evidence25 rows
Agentic
Terminal-Bench 2.0
GLM-4.6—MiniMax M2.757%SourceNot directly comparable
Toolathlon
GLM-4.6—MiniMax M2.746.3%SourceNot directly comparable
MLE-Bench Lite
GLM-4.6—MiniMax M2.766.6%SourceNot directly comparable
MM-ClawBench
GLM-4.6—MiniMax M2.762.7%SourceNot directly comparable
Claw-Eval
GLM-4.6—MiniMax M2.748.7%SourceNot directly comparable
Gert Labs
GLM-4.6—MiniMax M2.740.40%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
GLM-4.6—MiniMax M2.748.7%SourceNot directly comparable
Coding
Vibe Code Bench
Shared sourceGLM-4.63.09%MiniMax M2.727.04%MiniMax M2.7 leads this result
SWE-bench Verified*
GLM-4.6—MiniMax M2.775.4%SourceNot directly comparable
SWE-bench Pro
GLM-4.6—MiniMax M2.756.2%SourceNot directly comparable
SWE-Rebench
GLM-4.6—MiniMax M2.751.9%SourceNot directly comparable
SWE Multilingual
GLM-4.6—MiniMax M2.776.5%SourceNot directly comparable
Multi-SWE Bench
GLM-4.6—MiniMax M2.752.7%SourceNot directly comparable
VIBE-Pro
GLM-4.6—MiniMax M2.755.6%SourceNot directly comparable
NL2Repo
GLM-4.6—MiniMax M2.739.8%SourceNot directly comparable
React Native Evals
GLM-4.6—MiniMax M2.771.4%SourceNot directly comparable
LiveCodeBench (Vals)
GLM-4.6—MiniMax M2.779.9%SourceNot directly comparable
SWE-bench (Vals)
GLM-4.6—MiniMax M2.773.8%SourceNot directly comparable
Knowledge
Math
Frequently asked questions
Which is better, GLM-4.6 or MiniMax M2.7?
MiniMax M2.7 has the higher public score estimate, 58.98 versus 53.94, 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-4.6 or MiniMax M2.7?
MiniMax M2.7 scores higher for coding on the public lane, 50.5 to 48.8. GLM-4.6 and MiniMax M2.7 are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, GLM-4.6 or MiniMax M2.7?
GLM-4.6 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, GLM-4.6 or MiniMax M2.7?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, GLM-4.6 or MiniMax M2.7?
Both models list the same context window, 200K.
Related comparisons
Last updated September 4, 2026
Watch GLM-4.6 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.