Updated October 19, 2026. Rank says MiniMax M3.1 Flash is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
MiniMax M3.1 Flash has the higher public point estimate, 67.05 versus 54.96. Their conditional score ranges overlap. These ranges do not establish rank confidence. 3 results are shared. Category rows resting on Estimated evidence or 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.
Code generation, repair, and software-engineering tasks
MiniMax M3.1 Flash
MiniMax M3.1 Flash has the higher public coding point estimate, 61.3 to 37, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
1K fresh input + 500 output tokens
MiniMax M3.1 Flash
MiniMax M3.1 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
MiniMax M3.1 Flash
MiniMax M3.1 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
MiniMax M3.1 Flash
MiniMax M3.1 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Tool use, computer use, and multi-step task completion
Not enough matched evidence
MiniMax M3.1 Flash is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
Like-for-like · BenchAlign v5.8
MiniMax M3.1 Flash has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
OSWorld 2.0Agentic
Normalized gap 57.1Each row shows the public-lane category score for both models: the BenchAlign v5.8 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.
| Category | MiniMax M3 | MiniMax M3.1 Flash | Basis | Reading |
|---|---|---|---|---|
| Coding | 37.0Supported · #74/151 | 61.3Supported · #17/151 | Like-for-likeBenchAlign v5.8 lane · 10 vs 3 public rows | MiniMax M3.1 Flash leads · intervals overlap |
| Knowledge | 51.6Supported · #76/186 | 73.2Supported · #14/186 | Like-for-likeBenchAlign v5.8 lane · 2 vs 1 public rows | MiniMax M3.1 Flash leads |
| Agentic | 39.3Supported · #70/130 | 63.9Estimated · #19/130 | Directional onlyBenchAlign v5.8 lane · 10 vs 6 public rows | Directional only |
| Multimodal | 60.0#44/55 | 73.5#30/55 | Directional onlyProvisional lane · 2 vs 1 weighted rows | Directional only |
| Reasoning | 82.9Unranked · 2 rankable rows | 80.6Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 93.8#5/148 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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 M3.1 Flash has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
MiniMax M3.1 Flash has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
MiniMax M3.1 Flash has the lower modeled cost
Costs use the listed standard API rates.
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.
MiniMax M3
1M
MiniMax M3.1 Flash
MiniMax M3
Not sourced
MiniMax M3.1 Flash
MiniMax-M3.1-Flash
MiniMax: M3.1 Flash launch postA missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
MiniMax M3
$0.06 per 1M cached input tokens
MiniMax M3.1 Flash
$0.015 per 1M cached input tokens
MiniMax: M3.1 Flash launch postMiniMax M3
Not sourced
MiniMax M3.1 Flash
Not sourced
MiniMax M3
Not sourced
MiniMax M3.1 Flash
Not sourced
MiniMax M3
Not sourced
MiniMax M3.1 Flash
Not sourced
MiniMax M3
Non-Reasoning
MiniMax M3.1 Flash
Reasoning
MiniMax M3
Open Weight
MiniMax M3.1 Flash
Proprietary
MiniMax M3
Open Weight
MiniMax M3.1 Flash
Proprietary
MiniMax M3
2026-06-01
MiniMax M3.1 Flash
2026-10-19
MiniMax M3.1 Flash has the higher public point estimate, 67.05 versus 54.96. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
MiniMax M3.1 Flash has the higher public coding point estimate, 61.3 to 37, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
MiniMax M3.1 Flash scores higher for agentic tasks on the public lane, 63.9 to 39.3. MiniMax M3.1 Flash is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
For the stated presets, chat costs $0.0009 on MiniMax M3 and $0.00045 on MiniMax M3.1 Flash; repository review costs $0.0186 and $0.0093; the cache-heavy agent loop costs $0.03 and $0.012. Costs use the listed standard API rates.
Both models list the same context window, 1M.
Estimates at 50,000 req/day · 1000 tokens/req average.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 2.1
Not directly comparable
BrowseComp
Not directly comparable
OSWorld-Verified
Not directly comparable
MCP Atlas
Not directly comparable
Claw-Eval
Not directly comparable
BankerToolBench
MiniMax M3.1 Flash leads this result
ResearchClawBench
Not directly comparable
OSWorld 2.0
MiniMax M3.1 Flash leads this result
Terminal-Bench 2.1 (Vals)
Not directly comparable
MazeBench
Not directly comparable
AutomationBench
Not directly comparable
Terminal-Bench 4.0
Not directly comparable
Agents' Last Exam
Not directly comparable
CyberGym
Not directly comparable
SWE-bench Verified
Not directly comparable
SWE-bench Pro
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
NL2Repo
MiniMax M3.1 Flash leads this result
VIBE V2
Not directly comparable
SVG-Bench
Not directly comparable
KernelBench Hard
Not directly comparable
OpenHarmony Bench
Not directly comparable
LiveCodeBench (Vals)
Not directly comparable
SWE-bench (Vals)
Not directly comparable
PostTrainBench v1.1
Not directly comparable
DeepSWE
Not directly comparable
OfficeQA Pro
Not directly comparable
OmniDocBench 1.5
Not directly comparable
MMMU-Pro
Not directly comparable
VideoMMMU
Not directly comparable
Video-MME (with subtitle)
Not directly comparable
BabyVision w/ Python
Not directly comparable
CharXiv
Not directly comparable
USAMO 2026
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,600+ readers.
Last updated October 19, 2026
