Agentic
Like-for-like- Composer 2
- 61.7
- MiniMax M2.7
- 57.0
- Weighted basis
- 1 vs 1 rows
- Reading
- Composer 2 leads
Provider changes are easy to miss. Radar watches releases, pricing, deprecations, and incidents at the source.Provider changes are easy to miss.
See RadarModel comparison
Updated August 7, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
4 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
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.
Tool use, computer use, and multi-step task completion
Composer 2
Composer 2 leads on the same 1 weighted benchmark row.
Confidence: limited
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
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
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
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
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. Composer 2 does not fit this workload in one request. MiniMax M2.7 does not fit this workload in one request. Composer 2 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
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
| Category | Composer 2 | MiniMax M2.7 | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 61.7 | 57.0 | Like-for-like1 vs 1 rows | Composer 2 leads |
| Coding | 58.0 | 53.3 | Directional only1 vs 2 rows | Directional only |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Knowledge | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Math | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
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
Terminal-Bench 2.0
Agentic
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.
1K fresh input + 500 output tokens
MiniMax M2.7 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
MiniMax M2.7 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Composer 2 does not fit this workload in one request. MiniMax M2.7 does not fit this workload in one request. Composer 2 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.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
Composer 2
200K
MiniMax M2.7
200K
Composer 2
Not sourced
MiniMax M2.7
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Composer 2
Not published
MiniMax M2.7
Not published
Composer 2
Not sourced
MiniMax M2.7
Not sourced
Composer 2
Not sourced
MiniMax M2.7
Not sourced
Composer 2
Not sourced
MiniMax M2.7
Not sourced
Composer 2
Reasoning
MiniMax M2.7
Non-Reasoning
Composer 2
Proprietary
MiniMax M2.7
Open Weight
Composer 2
Proprietary
MiniMax M2.7
Open Weight
Composer 2
2026-03-19
MiniMax M2.7
2026-03-18
Run the same representative tasks against both endpoints before changing production traffic.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 2.0
Composer 2 leads this result
Toolathlon
Not directly comparable
MLE-Bench Lite
Not directly comparable
MM-ClawBench
Not directly comparable
Claw-Eval
Not directly comparable
Gert Labs
Not directly comparable
SWE Multilingual
MiniMax M2.7 leads this result
SWE-Rebench
Shared sourceComposer 2 leads this result
React Native Evals
Shared sourceComposer 2 leads this result
Terminal-Bench 2.0
Not directly comparable
SWE-bench Verified*
Not directly comparable
SWE-bench Pro
Not directly comparable
Multi-SWE Bench
Not directly comparable
VIBE-Pro
Not directly comparable
NL2Repo
Not directly comparable
Vibe Code Bench
Not directly comparable
AIME25 (Arcee)
Not directly comparable
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.
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.
Composer 2 leads the like-for-like agentic tasks comparison across 1 shared weighted benchmark row.
For the stated presets, chat costs $0.00175 on Composer 2 and $0.0009 on MiniMax M2.7; repository review costs $0.0325 and $0.0186; the cache-heavy agent loop costs $0.135 and $0.078. Composer 2 does not fit this workload in one request. MiniMax M2.7 does not fit this workload in one request. Composer 2 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.
Both models list the same context window, 200K.
Last updated August 7, 2026
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.