Agentic
Like-for-like- Claude Opus 4.6
- 73.0
- MiniMax M3
- 72.3
- Weighted basis
- 3 vs 3 rows
- Reading
- Claude Opus 4.6 leads
Claude Opus 4.6 vs MiniMax M3
Updated August 30, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
MiniMax M3 has the higher public score estimate, 68.73 versus 68.26, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
8 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
Claude Opus 4.6
Claude Opus 4.6 leads on the same 3 weighted benchmark rows.
Confidence: stronger
Chat turn cost
1K fresh input + 500 output tokens
MiniMax M3
MiniMax M3 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
MiniMax M3
MiniMax M3 has the lower estimated token cost for this stated workload. Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
MiniMax M3
MiniMax M3 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
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
25 Claude Opus 4.6 only
8 Shared
14 MiniMax M3 only
- Shared results
- 8
- Claude Opus 4.6 only
- 25
- MiniMax M3 only
- 14
- Like-for-like categories
- 1 / 8
2 categories use 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- Claude Opus 4.6
- 68.1
- MiniMax M3
- 72.2
- Weighted basis
- 3 vs 2 rows
- Reading
- Directional only
Multimodal
Directional only- Claude Opus 4.6
- 77.3
- MiniMax M3
- 64.9
- Weighted basis
- 1 vs 2 rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Opus 4.6
- Not measured
- MiniMax M3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude Opus 4.6
- 69.1
- MiniMax M3
- Not measured
- Weighted basis
- 4 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 4.6
- 36.3
- MiniMax M3
- 85.7
- Weighted basis
- 2 vs 1 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 4.6
- Not measured
- MiniMax M3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 4.6
- Not measured
- MiniMax M3
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Claude Opus 4.6 | MiniMax M3 | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 73.0 | 72.3 | Like-for-like3 vs 3 rows | Claude Opus 4.6 leads |
| Coding | 68.1 | 72.2 | Directional only3 vs 2 rows | Directional only |
| Multimodal | 77.3 | 64.9 | Directional only1 vs 2 rows | Directional only |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Knowledge | 69.1 | Not measured | Not comparable4 vs 0 rows | Not comparable |
| Math | 36.3 | 85.7 | Not comparable2 vs 1 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 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-bench Pro
Coding
OSWorld-Verified
Agentic
MMMU-Pro
Multimodal
Terminal-Bench 2.0
Agentic
SWE-bench Verified
Coding
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
- Claude Opus 4.6
- $0.0175
- Fits in one request
- MiniMax M3
- $0.0009
- Fits in one request
MiniMax M3 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 4.6
- $0.325
- Fits in one request
- MiniMax M3
- $0.0186
- Fits in one request
MiniMax M3 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Opus 4.6
- $1.35
- Fits in one request
- Cached input priced at the published list-input rate
- MiniMax M3
- $0.03
- Fits in one request
MiniMax M3 has the lower modeled cost
Claude Opus 4.6 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.
SpecificationClaude Opus 4.6MiniMax M3
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 4.6
1M
MiniMax M3
1M
API model ID
Claude Opus 4.6
Not sourced
MiniMax M3
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 4.6
Not published
MiniMax M3
$0.06 per 1M cached input tokens
Documented inputs
Claude Opus 4.6
Not sourced
MiniMax M3
Not sourced
Documented outputs
Claude Opus 4.6
Not sourced
MiniMax M3
Not sourced
Provider availability
Claude Opus 4.6
Not sourced
MiniMax M3
Not sourced
Reasoning profile
Claude Opus 4.6
Non-Reasoning
MiniMax M3
Non-Reasoning
Weight access
Claude Opus 4.6
Proprietary
MiniMax M3
Open Weight
License
Claude Opus 4.6
Proprietary
MiniMax M3
Open Weight
Release date
Claude Opus 4.6
2026-02-01
MiniMax M3
2026-06-01
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 M3 has the higher public score estimate, 68.73 versus 68.26, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.325 vs $0.0186. Cache-heavy agent loop: $1.35 vs $0.03.
- Context tradeoff
- Both models list 1M.
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 evidence47 rows
Agentic
Terminal-Bench 2.0
Claude Opus 4.665.4%SourceMiniMax M366%SourceMiniMax M3 leads this result
BrowseComp
Claude Opus 4.683.7%SourceMiniMax M383.5%SourceClaude Opus 4.6 leads this result
OSWorld-Verified
Claude Opus 4.672.7%SourceMiniMax M370.1%SourceClaude Opus 4.6 leads this result
Claw-Eval
Claude Opus 4.670.4%SourceMiniMax M374.5%SourceMiniMax M3 leads this result
DeepSearchQA
Claude Opus 4.673.7%SourceMiniMax M3—Not directly comparable
CyberGym
Claude Opus 4.666.6%SourceMiniMax M3—Not directly comparable
Gert Labs
Claude Opus 4.661.85%SourceMiniMax M3—Not directly comparable
ResearchClawBench
Shared sourceClaude Opus 4.619.9%MiniMax M319.8%Claude Opus 4.6 leads this result
JobBench
Claude Opus 4.636.7%SourceMiniMax M3—Not directly comparable
MCP Atlas
Claude Opus 4.6—MiniMax M374.2%SourceNot directly comparable
BankerToolBench
Claude Opus 4.6—MiniMax M376.1%SourceNot directly comparable
OSWorld 2.0
Claude Opus 4.6—MiniMax M34.6%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Opus 4.680.8%SourceMiniMax M380.5%SourceClaude Opus 4.6 leads this result
SWE-bench Verified*
Claude Opus 4.675.6%SourceMiniMax M3—Not directly comparable
LiveCodeBench Pro
Claude Opus 4.670.7%SourceMiniMax M3—Not directly comparable
SWE-bench Pro
Claude Opus 4.653.4%SourceMiniMax M359%SourceMiniMax M3 leads this result
SWE-Rebench
Claude Opus 4.665.3%SourceMiniMax M3—Not directly comparable
React Native Evals
Claude Opus 4.684.1%SourceMiniMax M3—Not directly comparable
Vibe Code Bench
Claude Opus 4.657.57%SourceMiniMax M3—Not directly comparable
FrontierCode 1.1 Main
Claude Opus 4.626.9%SourceMiniMax M3—Not directly comparable
Terminal-Bench 2.0
Claude Opus 4.6—MiniMax M366.0%SourceNot directly comparable
NL2Repo
Claude Opus 4.6—MiniMax M342.1%SourceNot directly comparable
VIBE V2
Claude Opus 4.6—MiniMax M350.1%SourceNot directly comparable
SVG-Bench
Claude Opus 4.6—MiniMax M363.7%SourceNot directly comparable
KernelBench Hard
Claude Opus 4.6—MiniMax M328.8%SourceNot directly comparable
OpenHarmony Bench
Claude Opus 4.6—MiniMax M348.4%SourceNot directly comparable
Knowledge
GPQA
Claude Opus 4.691.3%SourceMiniMax M3—Not directly comparable
GPQA-D
Claude Opus 4.689.2%SourceMiniMax M3—Not directly comparable
SuperGPQA
Claude Opus 4.695%SourceMiniMax M3—Not directly comparable
MMLU-Pro
Claude Opus 4.682%SourceMiniMax M3—Not directly comparable
MMLU-Pro (Arcee)
Claude Opus 4.689.1%SourceMiniMax M3—Not directly comparable
HLE
Claude Opus 4.653%SourceMiniMax M3—Not directly comparable
HLE w/o tools
Claude Opus 4.640%SourceMiniMax M3—Not directly comparable
HealthBench Hard
Claude Opus 4.614.8%SourceMiniMax M3—Not directly comparable
MedXpertQA (Text)
Claude Opus 4.652.1%SourceMiniMax M3—Not directly comparable
Math
AIME25 (Arcee)
Claude Opus 4.699.8%SourceMiniMax M3—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Claude Opus 4.640.700%SourceMiniMax M3—Not directly comparable
FrontierMath v2 (Tier 4)
Claude Opus 4.622.900%SourceMiniMax M3—Not directly comparable
USAMO 2026
Claude Opus 4.6—MiniMax M385.7%SourceNot directly comparable
Multimodal
MMMU-Pro
Claude Opus 4.677.3%SourceMiniMax M378.1%SourceMiniMax M3 leads this result
ERQA
Claude Opus 4.651.6%SourceMiniMax M3—Not directly comparable
ScreenSpot Pro
Claude Opus 4.683.1%SourceMiniMax M3—Not directly comparable
MedXpertQA (MM)
Claude Opus 4.664.8%SourceMiniMax M3—Not directly comparable
OfficeQA Pro
Claude Opus 4.6—MiniMax M345.1%SourceNot directly comparable
OmniDocBench 1.5
Claude Opus 4.6—MiniMax M391.6%SourceNot directly comparable
VideoMMMU
Claude Opus 4.6—MiniMax M384.6%SourceNot directly comparable
Video-MME (with subtitle)
Claude Opus 4.6—MiniMax M385.4%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Opus 4.6 or MiniMax M3?
MiniMax M3 has the higher public score estimate, 68.73 versus 68.26, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Claude Opus 4.6 or MiniMax M3?
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, Claude Opus 4.6 or MiniMax M3?
Claude Opus 4.6 leads the like-for-like agentic tasks comparison across 3 shared weighted benchmark rows.
Which costs less, Claude Opus 4.6 or MiniMax M3?
For the stated presets, chat costs $0.0175 on Claude Opus 4.6 and $0.0009 on MiniMax M3; repository review costs $0.325 and $0.0186; the cache-heavy agent loop costs $1.35 and $0.03. Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Opus 4.6 or MiniMax M3?
Both models list the same context window, 1M.
Related comparisons
Last updated August 30, 2026
Watch Claude Opus 4.6 vs MiniMax M3
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.