Qwen3.6 Max vs Step 5 Preview
Full profiles: Qwen3.6 Max (Alibaba) and Step 5 Preview (StepFun): every benchmark, price and rank.
Updated · Data from 6 sources
As of 16 Nov 2026, Qwen3.6 Max is ahead of Step 5 Preview on quality (62.1 vs 56.0 on the BenchLeader Index), but Step 5 Preview is 2.1× cheaper at $1.43 vs $2.92 per 1M tokens blended. Choose Qwen3.6 Max for agents & tools (72 vs 49), reasoning (61 vs 52), and coding (56 vs 50); choose Step 5 Preview for long context (69 vs 65).
Key facts (as of 16 Nov 2026)
- Qwen3.6 Max scores 62.1 on the BenchLeader Index and Step 5 Preview scores 56.0 (BenchLeader, 16 Nov 2026).
- Qwen3.6 Max costs $2.92 per 1M tokens blended (list price, 16 Nov 2026).
- Step 5 Preview costs $1.43 per 1M tokens blended (list price, 16 Nov 2026).
- Of the 12 benchmarks both models have, Qwen3.6 Max leads 8 (BenchLeader, 16 Nov 2026).
Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Qwen3.6 Max | 56 vs 50 category score; Arena Coding 1510 vs 1505 | Medium |
| Agents & tool use | Qwen3.6 Max | 72 vs 49 category score | High |
| Maths | Qwen3.6 Max | 64 vs 60 category score; Arena Maths 1471 vs 1470 | Medium |
| Reasoning | Qwen3.6 Max | 61 vs 52 category score; Arena Hard Prompts 1481 vs 1477 | High |
| Knowledge | Qwen3.6 Max | 60 vs 54 category score | Medium |
| Long documents | Step 5 Preview | 69 vs 65 category score; AA-LCR v1.1 88.3% vs 80.7% | Medium |
| Chat quality (human preference) | Qwen3.6 Max | 65 vs 63 on Arena votes | Medium |
| Lowest cost | Step 5 Preview | $1.43 vs $2.92 per 1M blended; agentic coding session $0.071 vs $0.109 | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Qwen3.6 Max (max) leads on quality: 62.1 vs 56.0.
- Qwen3.6 Max (max) is stronger in agents & tools, coding, human preference, knowledge, maths, reasoning.
- Step 5 Preview is stronger in long context.
- Step 5 Preview is 2.1× cheaper ($1.43 vs $2.92 per 1M blended).
At a glance
| Spec | Qwen3.6 Max | Step 5 Preview |
|---|---|---|
| Developer | Alibaba | StepFun |
| Released | 20 Apr 2026 | 18 Sep 2026 |
| Context window (tokens) | 262,144 | 1,000,000 |
| Compared at | Qwen3.6 Max (max) | Step 5 Preview |
| Open weights | No | Yes |
| Price in / out / cached input per 1M | $1.30 / $7.80 / $0.130 | $1.00 / $2.70 / $0.105 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | Qwen3.6 Max (max) | Step 5 Preview | Leader |
|---|---|---|---|
| Reasoning | 60.8 | 51.7 | Qwen3.6 Max |
| Coding | 55.9 | 49.9 | Qwen3.6 Max |
| Agents & tools | 72.1 | 49.1 | Qwen3.6 Max |
| Maths | 64.4 | 60.1 | Qwen3.6 Max |
| Knowledge | 59.7 | 53.7 | Qwen3.6 Max |
| Instruction following | 74.7 | – | not comparable |
| Human preference | 64.5 | 63.1 | Qwen3.6 Max |
| Multimodal | – | 59.3 | not comparable |
| Long context | 65.0 | 69.0 | Step 5 Preview |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Instruction following, Multimodal.
Where sources disagree
Across the 12 benchmarks both have, Qwen3.6 Max leads 8, Step 5 Preview leads 4. Every overall index that rates both puts Qwen3.6 Max ahead.
| Overall index | Qwen3.6 Max (max) | Step 5 Preview | Leader |
|---|---|---|---|
| BenchLeader Index | 62.1 | 56.0 | Qwen3.6 Max |
| Arena Text | 1460 | 1449 | Qwen3.6 Max |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Qwen3.6 Max (max) | Step 5 Preview |
|---|---|---|
| Blended price per 1M tokens | $2.92 | $1.43 |
| Input / output per 1M | $1.30 / $7.80 | $1.00 / $2.70 |
| Cached input per 1M | $0.130 | $0.105 |
| Price per task: chat reply | $0.0029 | $0.0012 |
| Price per task: summarize a 30-page report | $0.020 | $0.014 |
| Price per task: code edit | $0.019 | $0.010 |
| Price per task: agentic coding session | $0.109 | $0.071 |
| Price per task: structured extraction | $0.0042 | $0.0025 |
| Agentic coding session, input mostly cached | $0.057 | $0.030 |
| Cost per benchmark task (AA Index) | – | $2.35 |
| Output tokens per task (AA Index) | – | 113k |
| Of which reasoning | – | 80k |
| Time per task (AA Index) | – | 15 min |
| Output speed | – | 124 tok/s |
| Time to first answer | – | 23.5 s |
| Time to a complete answer, last measured 13 Nov 2026 | – | 54.4 s |
Each model is compared at its best-ranked reasoning-effort setting. Qwen3.6 Max (max) scores 62.1. Step 5 Preview scores 56.0 and takes 24 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
98 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | Qwen3.6 Max (max) | Step 5 Preview |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 62.1 | 56.0 |
| Agents & tools score | BenchLeader | 72.1 | 49.1 |
| Coding score | BenchLeader | 55.9 | 49.9 |
| Human preference score | BenchLeader | 64.5 | 63.1 |
| Instruction following score | BenchLeader | 74.7 | – |
| Knowledge score | BenchLeader | 59.7 | 53.7 |
| Long context score | BenchLeader | 65.0 | 69.0 |
| Maths score | BenchLeader | 64.4 | 60.1 |
| Reasoning score | BenchLeader | 60.8 | 51.7 |
| Multimodal score | BenchLeader | – | 59.3 |
| Blended price $/M | BenchLeader | $2.92 | $1.43 |
| Output speed | BenchLeader | – | 124 tok/s |
| Time to first answer | BenchLeader | – | 23.5 s |
| Context window | BenchLeader | 262,144 tokens | 1,000,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 87.4% | – |
| SimpleBench | SimpleBench | 63.0% | – |
| Arena Hard Prompts | Arena (LMArena) | 1481 | 1477 |
| LiveBench 2.0 Reasoning | LiveBench | – | 83.8%† |
| GPQA Diamond (AA) | Artificial Analysis | 88.8% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 30.8% | 46.5% |
| HLE-Diamond (AA) | Artificial Analysis | – | 24.3% |
| CritPt | Artificial Analysis | 3.7% | 20.9% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 32.5% |
| MysteryMechanism | Vals AI | – | 18.5% |
| Arena Expert | Arena (LMArena) | 1497 | 1489 |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 19.0%† | – |
| LMCA | Epoch AI Benchmarking Hub | 42.5% | – |
| DTBench | Epoch AI Benchmarking Hub | 87.2% | – |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | 76.7% | – |
| SciCode | SciCode | – | 58.9% |
| Arena Coding | Arena (LMArena) | 1510 | 1505 |
| Arena WebDev | Arena (LMArena) | 1482 | 1573† |
| LiveBench 2.0 Coding | LiveBench | – | 67.6%† |
| IOI | Vals AI | – | 38.1% |
| SWE-bench (Vals) | Vals AI | 72.8% | – |
| Code Migration | Vals AI | – | 39.0% |
| Code Migration v1.1 | Vals AI | – | 47.0% |
| SWE-bench Multimodal | Vals AI | – | 40.8% |
| Vibe Code Bench v1.1 | Vals AI | – | 70.4% |
Show all 98 benchmarks
| Metric | Publisher | Qwen3.6 Max (max) | Step 5 Preview |
|---|---|---|---|
| Coding | |||
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 33.3% |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 38.4% |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 12.0% |
| Agents & tools | |||
| Arena Agent | Arena (LMArena) | – | -3.7 |
| LiveBench Long Agentic | LiveBench | – | 19.4%† |
| LiveBench Browser | LiveBench | – | 24.8%† |
| Terminal-Bench Hard | Artificial Analysis | 43.9% | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 95.9% | – |
| GDPval-AA v2.1, normalised score | Artificial Analysis | – | 54.3% |
| GDPval-AA v2.1 | Artificial Analysis | – | 1591 |
| ITBench SRE (AA) | Artificial Analysis | – | 55.6% |
| Analyst Agent (AA) | Artificial Analysis | – | 35.0% |
| APEX-Agents (AA) | Artificial Analysis | – | 38.0% |
| Finance Agent v2 | Vals AI | – | 50.7% |
| Finance Agent v2.1 | Vals AI | – | 58.9% |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 12.9% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 9.2% |
| Legal Research Bench | Vals AI | – | 40.4% |
| SREBench | Vals AI | – | 0.4% |
| Tax Agent Bench | Vals AI | – | 27.3% |
| Terminal-Bench 2.0 (Vals) | Vals AI | 51.7% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 31.8% |
| Terminal-Bench Science | Vals AI | – | 2.9% |
| Arena Agent Task Completion | Arena (LMArena) | – | -1.5 |
| Vending-Bench 2 | Andon Labs | 4254.2 | – |
| AutomationBench | Artificial Analysis | – | 51.0% |
| GDP.pdf (AA) | Artificial Analysis | – | 14.8% |
| EnterpriseOps-Gym | Artificial Analysis | – | 47.2% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1424 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 2.4% |
| CWE-Bench (AA) | Artificial Analysis | – | 52.5% |
| DeepSec-Bench (AA) | Artificial Analysis | – | 15.8% |
| CyberGym end-to-end (AA) | Artificial Analysis | – | 74.8% |
| MKA (AA) | Artificial Analysis | – | 27.6% |
| Maths | |||
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 91.1% | – |
| ProofBench | Vals AI | – | 42.0% |
| Arena Maths | Arena (LMArena) | 1471 | 1470 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 52.0% | – |
| LiveBench 2.0 Data Analysis | LiveBench | – | 63.5%† |
| LiveBench Research | LiveBench | – | 75.5%† |
| AA-Omniscience v1.1 | Artificial Analysis | – | 16.4 |
| CorpFin | Vals AI | 66.5% | – |
| BioMysteryBench | Vals AI | – | 67.4% |
| CaseLaw v2 | Vals AI | 47.9% | – |
| Excel Modeling Benchmark | Vals AI | – | 57.1% |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 69.5% |
| Public Benefits Bench v1.1 | Vals AI | – | 58.1% |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 36.4% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 68.7% |
| Instruction following | |||
| IFBench | Artificial Analysis | 76.6% | – |
| Arena Instruction Following | Arena (LMArena) | 1451 | 1450 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1460 | 1449 |
| Arena Creative Writing | Arena (LMArena) | 1438 | 1413 |
| Arena Multi-turn | Arena (LMArena) | 1466 | 1445 |
| Arena Longer Queries | Arena (LMArena) | 1473 | 1461 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1263 |
| LiveBench Design | LiveBench | – | 70.8%† |
| MMMU-Pro | Artificial Analysis | – | 76.4% |
| Code2Video-AA | Artificial Analysis | – | 821 |
| AA-3D | Artificial Analysis | – | 859 |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 80.7% | 88.3% |
| MLCR | Artificial Analysis | – | 18.3% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 149.8 | – |
| LiveBench 2.0 | LiveBench | – | 54.9%† |
| AA Intelligence Index v5.0.1 | Artificial Analysis | – | 28.5 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 28.4 | 43.7 |
| AA Progress Index v1 | Artificial Analysis | 297.1 | 318.2 |
| Vals Index | Vals AI | – | 54.8 |
| Vals Finance Index | Vals AI | – | 55.4% |
| Vals Science Index | Vals AI | – | 29.6% |
| Vals Legal Index | Vals AI | – | 70.2% |
| AA Cyber Index | Artificial Analysis | – | 47.7 |
| Metadata | |||
| AA Openness Index | Artificial Analysis | – | 33.3 |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
What changed
- Step 5 Preview: BenchLeader Index 54.2 → 56.0.
- Step 5 Preview: BenchLeader Index 54.7 → 54.2.
- Step 5 Preview: 1 score revision.
- Qwen3.6 Max (max): BenchLeader Index 62.8 → 62.3.
- Step 5 Preview: 7 score revisions.
- Step 5 Preview: 2 new results (Vals Index, Harvey's Legal Agent Benchmark v1.1).
- Step 5 Preview: 1 score revision.
- Step 5 Preview: BenchLeader Index 58.0 → 54.7.
- Qwen3.6 Max (max): 1 new result (AA Progress Index v1).
- Step 5 Preview: 5 new results (AA Intelligence Index v5.0.1, AA Progress Index v1, HLE-Diamond (AA)…); 2 score revisions; Step 5 Preview cost per task moved from $1.03/M to $2.35/M (128% up).
Related comparisons
- Qwen3.6 Max vs Claude Fable 5.2
- Qwen3.6 Max vs Gemini 4 Carbon
- Qwen3.6 Max vs Claude Opus 5.5
- Step 5 Preview vs Claude Opus 5.5
- Step 5 Preview vs GPT-6 Astra
- Step 5 Preview vs GPT-6.1 Sol
- Step 5 Preview vs Gemini 4 Argon
- Qwen3.6 Max vs Claude Fable 5.1
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Qwen3.6 Max vs Step 5 Preview: questions
- Is Qwen3.6 Max better than Step 5 Preview?
- Qwen3.6 Max (max) leads on quality: 62.1 vs 56.0. The BenchLeader Index combines every independent quality benchmark; Qwen3.6 Max (max) is ahead overall as of 16 Nov 2026, but check the category scores for your use.
- Qwen3.6 Max vs Step 5 Preview: which is cheaper, and will that change?
- Step 5 Preview is cheaper today: $1.43 against $2.92 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Qwen3.6 Max or Step 5 Preview better for coding?
- Qwen3.6 Max scores higher in coding (56 vs 50 on the category index, where 50 is average). On Arena Coding, the top shared coding benchmark, it is 1510 for Qwen3.6 Max against 1505 for Step 5 Preview.
- Is Qwen3.6 Max or Step 5 Preview better for agents and tool use?
- Qwen3.6 Max scores higher in agentic tasks (72 vs 49 on the category index, where 50 is average).
- Which is better for long documents?
- Step 5 Preview scores higher on long-context benchmarks (69 vs 65). Step 5 Preview accepts more context: 1,000,000 against 262,144 tokens for Qwen3.6 Max.
More questions (2)
- Do independent benchmarks agree on Qwen3.6 Max vs Step 5 Preview?
- Across the 12 benchmarks both have, Qwen3.6 Max leads 8, Step 5 Preview leads 4. Every overall index that rates both puts Qwen3.6 Max ahead.
- When was Step 5 Preview released?
- Step 5 Preview was released on 18 Sep 2026.