Across 2 comparable benchmarks, Qwen3-Max-Thinking and MiniMax M3.1 Flash are evenly matched at 1 apiece.
Limited evidence2 of 2 shared results countedHow we compare
Price basis: Listed rates vs standard rates. The price section below shows the applicable periods.
| Fact | Qwen3-Max-Thinking | MiniMax M3.1 Flash |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | — | $0.150 |
| Output / 1M | — | $0.600 |
| Blended (4:1) | — | $0.143 |
| Status | Deprecated | Available |
| Released | January 26, 2026 | October 19, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 1 shared benchmark grouped by capability on a 0–100 scale. How averages are built
MiniMax M3.1 Flash ahead on 1 of 1 counted
No shared comparable results for Abstract reasoning, Mathematics, Science & health, Computer & tool use, Research & search, Long context, Multimodal, Professional work & productivity, Cybersecurity.
Published scores, with matching modes where available. Gaps show Qwen3-Max-Thinking relative to MiniMax M3.1 Flash. Reading the results
| Benchmark | Qwen3-Max-Thinking | MiniMax M3.1 Flash | Gap |
|---|---|---|---|
| Vibe Code Bench v1.1Code Generation & Editing · Pass rate (%) | 3.5Unspecified Reasoning · tools | 73.9≠Max · tools | −70.4 pts#110 vs #46 of 121 |
| HLEKnowledge Exams · Accuracy | 49.8Thinking · tools | 48.0≠Reported best | +1.8 pts#51 vs #58 of 151 |
Code Generation & Editing · Pass rate (%)
Knowledge Exams · Accuracy
A dash means no result is available.
| Benchmark | Qwen3-Max-Thinking | MiniMax M3.1 Flash |
|---|---|---|
| C-Eval | 93.7 | — |
| CritPt | 1.7 | — |
| GPQA Diamond | 87.4 | — |
| HLE-Verified | 38.2 | — |
| IMO-AnswerBench | 83.9 | — |
| MMLU-Pro | 85.7 | — |
| DeepSWE | — | 73.7 |
| FrontierCS 2 | — | 3.3 |
| LiveCodeBench | 85.9 | — |
| NL2Repo-Bench | — | 61.2 |
| PostTrain Bench | — | 39.3 |
| SWE Refactor Bench | — | 23.0 |
| SWE-bench Verified | 75.3 | — |
| SWE-sweep | — | 0.67 |
| Terminal Bench Hard | 24.2 | — |
| Terminal-Bench 4.0 | — | 38.1 |
| Agents' Last Exam v1.0 | — | 29.6 |
| Agents' Last Exam v1.1 | — | 29.5 |
| AutomationBench-AA | — | 72.5 |
| OSWorld 2.0 | — | 61.7 |
| Pinch Bench | 80.3 | — |
| CyberGym | — | 82.2 |
| AA Intelligence Index v4.3 | — | 42.4 |
| AA Intelligence Index v5.0.1 | — | 29.1 |
| Code Arena WebDev | — | 1588 |
| LiveBench 2.0 | — | 73.1 |
| Vals Index v2.2 | — | 53.8 |
| IF Bench | 70.9 | — |
| LOCA-Bench 256K | — | 60.3 |
| BabyVision | — | 91.0 |
| CharXiv RQ | — | 82.5 |
| MMMU-Pro | — | 79.1 |
| AutomationBench | — | 62.8 |
| BankerToolBench | — | 76.2 |
| GDPx | — | 4.0 |
| Legal Research Bench | — | 34.1 |
| Tax Agent Bench | — | 32.1 |
| τ²-Bench | 82.1 | — |
| MedCode | 31.4 | — |
| MedScribe | 72.7 | — |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
A blended cost needs a published input and output price on both sides, and one of these two does not have them yet.
Qwen3-Max-Thinking: Listed text rates; pricing tier not confirmed.
MiniMax M3.1 Flash: Standard pricing. MiniMax international platform (platform.minimax.io) pay-as-you-go list price, flat across context lengths. Official independent currency quote; no conversion.
| Price / 1M tokens | Qwen3-Max-Thinking | MiniMax M3.1 Flash | Ratio |
|---|---|---|---|
| Input | — | $0.15 | — |
| Output | — | $0.60 | — |
| Cached input | — | $0.015 | — |
| Cache write | — | — | — |
| Blended | — | $0.143 | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
Qwen3-Max-Thinking relative to MiniMax M3.1 Flash
No matching recorded settings for a cost summary.
Summary: 0 of 1 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 0 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Settings or sources differ
Settings or sources differ
Settings or sources differ or are not recorded; interpret the comparison with care.
Qwen3-Max-Thinking
MiniMax M3.1 Flash
| Benchmark | Qwen3-Max-Thinking | MiniMax M3.1 Flash |
|---|---|---|
| AA Intelligence Index v5.0.1 | Not reported | |
| Agents' Last Exam v1.0 | Not reported | |
| AutomationBench-AA | Not reported | $0.0665 / task Average · Guardrail-safe objective completion rate: 72.5 Thinking (With Tools) |
| FrontierCS 2 | Not reported | |
| GDPx | Not reported | $1.61 / task Average · GDPx — Score: 4.0 Highest (source-reported) (With Tools) · overall/score |
| HLE | Not reported | |
| Legal Research Bench | Not reported | |
| LiveBench 2.0 | Not reported | $0.1056 / task Average · Overall score (equal-weight mean of 7 suite scores, 0-100): 73.1 Max (task-specific tools) |
| MedCode | Not reported | |
| MedScribe | Not reported | |
| SWE-sweep | Not reported | |
| Tax Agent Bench | Not reported | $0.3209 / task Average · Accuracy (%, rubric × citation quality): 32.1 Unspecified Reasoning (With Tools) |
| Terminal-Bench 4.0 | Not reported | $0.73 / task Average · Resolution rate (%): 25.3 Unspecified Reasoning (With Tools) · vals-mini-swe |
| Vals Index v2.2 | Not reported |
| Attribute | Qwen3-Max-Thinking | MiniMax M3.1 Flash |
|---|---|---|
| Availability | Deprecated | Available |
| Provider | Alibaba | MiniMaxAI |
| Model type | Reasoning model | Coding model |
| First release | January 26, 2026 | October 19, 2026 |
| Context window | 1M tokens | 1M tokens |
| Max output | 32K tokens | — |
| Total parameters | 1.0T | 428B |
| Active parameters | — | 23B |
| Architecture | Dense | Mixture of Experts (MoE) |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Coding |
| Knowledge cutoff | 2024-10 | — |
| Input modalities | Text | Text, Image, Video |
| Output modalities | Text | Text |
| Weights | Closed / API only | Open weights |
| Licence | — | MiniMax M3.1-Flash Community License |
| Commercial use | Proprietary | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Qwen3-Max-Thinking or MiniMax M3.1 Flash? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.