Gemini 3.6 Flash vs Qwen3.8 Max
Full profiles: Gemini 3.6 Flash (Google) and Qwen3.8 Max (Alibaba): every benchmark, price and rank.
Updated · Data from 15 sources
As of 16 Nov 2026, Gemini 3.6 Flash and Qwen3.8 Max are neck and neck on quality (61.0 vs 58.7 on the BenchLeader Index, inside the ±4.5 margin), and Gemini 3.6 Flash is 2.0× cheaper at $1.50 vs $3.00 per 1M tokens blended. Choose Gemini 3.6 Flash for reasoning (64 vs 52) and knowledge (64 vs 58) and fast first answers (11.0 s vs 119.6 s), where it also streams 3×+ faster; choose Qwen3.8 Max for maths (65 vs 59) and coding (62 vs 57). Gemini 3.6 Flash's current price runs until 31 Dec 2026, then $3.00.
Key facts (as of 16 Nov 2026)
- Gemini 3.6 Flash scores 61.0 on the BenchLeader Index and Qwen3.8 Max scores 58.7 (BenchLeader, 16 Nov 2026).
- Gemini 3.6 Flash costs $1.50 per 1M tokens blended until 31 Dec 2026, then $3.00 (https://ai.google.dev/gemini-api/docs/pricing, checked 20 Oct 2026).
- Qwen3.8 Max costs $3.00 per 1M tokens blended (list price, 16 Nov 2026).
- Gemini 3.6 Flash streams 3×+ faster than Qwen3.8 Max (Artificial Analysis, 7-day median, 16 Nov 2026).
- Of the 60 benchmarks both models have, Qwen3.8 Max leads 42 (BenchLeader, 16 Nov 2026).
- On Arena WebDev, Gemini 3.6 Flash is rated 1538 and Qwen3.8 Max 1676 (LMArena, as published by 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 | Qwen3.8 Max | 62 vs 57 category score; Arena WebDev 1676 vs 1538 | Medium |
| Agents & tool use | Either | 59 vs 59 category score; τ³-Banking (AA) 29.9% vs 51.3% | Either |
| Maths | Qwen3.8 Max | 65 vs 59 category score; Arena Maths 1505 vs 1501 | Medium |
| Reasoning | Gemini 3.6 Flash | 64 vs 52 category score; Arena Hard Prompts 1501 vs 1507 | High |
| Knowledge | Gemini 3.6 Flash | 64 vs 58 category score; MMLU-Pro 89.3% vs 88.6% | Medium |
| Long documents | Either | 65 vs 65 category score; AA-LCR v1.1 80.0% vs 80.3% | Either |
| Images and other media | Either | 65 vs 66 category score; Arena Vision 1297 vs 1312 | Either |
| Chat quality (human preference) | Either | 67 vs 68 on Arena votes | Either |
| Lowest cost | Gemini 3.6 Flash (until 31 Dec 2026) | $1.50 vs $3.00 per 1M blended; agentic coding session $0.060 vs $0.144; from 1 Jan 2027: $3.00 vs $3.00 | – |
| Fastest first answer | Gemini 3.6 Flash | 11.0 s (Gemini 3.6 Flash (high)) vs 119.6 s (Qwen3.8 Max (max)) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Gemini 3.6 Flash (high) and Qwen3.8 Max (max) are neck and neck on quality (61.0 vs 58.7, within the ±4.5 margin).
- Gemini 3.6 Flash (high) is stronger in agents & tools, knowledge, reasoning.
- Qwen3.8 Max (max) is stronger in coding, human preference, long context, maths, multimodal.
- Gemini 3.6 Flash (high) is 2.0× cheaper ($1.50 vs $3.00 per 1M blended) until 31 Dec 2026, then $3.00 vs $3.00 from 1 Jan 2027.
- Gemini 3.6 Flash (high) streams 3.0× faster (177 vs 59 tokens per second).
At a glance
| Spec | Gemini 3.6 Flash | Qwen3.8 Max |
|---|---|---|
| Developer | Alibaba | |
| Released | 21 Jul 2026 | 3 Aug 2026 |
| Context window (tokens) | 1,048,576 | 1,000,000 |
| Compared at | Gemini 3.6 Flash (high) | Qwen3.8 Max (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $0.750 / $3.75 / $0.075 | $2.00 / $6.00 / $0.250 |
| Announced price change | $1.50 / $7.50 / $0.150 from 1 Jan 2027 | None announced |
Limits, availability and announced prices from the vendors' own pages: ai.google.dev pricing (checked 20 Oct 2026). Everything else is from the day's data.
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 | Gemini 3.6 Flash (high) | Qwen3.8 Max (max) | Leader |
|---|---|---|---|
| Reasoning | 63.6 | 51.5 | Gemini 3.6 Flash |
| Coding | 56.7 | 61.6 | Qwen3.8 Max |
| Agents & tools | 59.2 | 58.5 | level |
| Maths | 59.0 | 65.2 | Qwen3.8 Max |
| Knowledge | 63.6 | 58.0 | Gemini 3.6 Flash |
| Human preference | 67.3 | 67.5 | level |
| Multimodal | 65.0 | 65.7 | level |
| Long context | 64.6 | 64.8 | level |
| Composite | – | 45.0 | not comparable |
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.
Where sources disagree
Across the 60 benchmarks both have, Gemini 3.6 Flash leads 16, Qwen3.8 Max leads 42 and 2 are tied. Every overall index that rates both puts Qwen3.8 Max ahead.
| Overall index | Gemini 3.6 Flash (high) | Qwen3.8 Max (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 61.0 | 58.7 | neck and neck |
| Arena Text | 1483 | 1484 | Qwen3.8 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 | Gemini 3.6 Flash (high) | Qwen3.8 Max (max) |
|---|---|---|
| Blended price per 1M tokens, until 31 Dec 2026 | $1.50 | $3.00 |
| Input / output per 1M | $0.750 / $3.75 | $2.00 / $6.00 |
| Blended price per 1M from 1 Jan 2027 | $3.00 | $3.00 |
| Input / output per 1M from 1 Jan 2027 | $1.50 / $7.50 | $2.00 / $6.00 |
| Cached input per 1M | $0.075 | $0.250 |
| Price per task: chat reply | $0.0014 | $0.0026 |
| Price per task: summarize a 30-page report | $0.011 | $0.028 |
| Price per task: code edit | $0.010 | $0.021 |
| Price per task: agentic coding session | $0.060 | $0.144 |
| Price per task: structured extraction | $0.0023 | $0.0052 |
| Agentic coding session, input mostly cached | $0.030 | $0.065 |
| Cost per benchmark task (AA Index) | – | $10.02 |
| Output tokens per task (AA Index) | – | 171k |
| Of which reasoning | – | 120k |
| Time per task (AA Index) | – | 48 min |
| Output speed | 177 tok/s | 59 tok/s |
| Time to first answer | 11.0 s | 119.6 s |
| Time to a complete answer, last measured 13 Nov 2026 | 30.3 s | 294.1 s |
Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.6 Flash (high) scores 61.0 and takes 11 s to its first answer token; Gemini 3.6 Flash scores 49.3 in 1 s. Qwen3.8 Max (max) scores 58.7 and takes 120 s to its first answer token; Qwen3.8 Max (xhigh) scores 56.6 in 3 s. 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
148 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 | Gemini 3.6 Flash (high) | Qwen3.8 Max (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 61.0 | 58.7 |
| Agents & tools score | BenchLeader | 59.2 | 58.5 |
| Coding score | BenchLeader | 56.7 | 61.6 |
| Human preference score | BenchLeader | 67.3 | 67.5 |
| Knowledge score | BenchLeader | 63.6 | 58.0 |
| Long context score | BenchLeader | 64.6 | 64.8 |
| Maths score | BenchLeader | 59.0 | 65.2 |
| Multimodal score | BenchLeader | 65.0 | 65.7 |
| Reasoning score | BenchLeader | 63.6 | 51.5 |
| Composite score | BenchLeader | – | 45.0 |
| Blended price $/M | BenchLeader | $1.50 | $3.00 |
| Output speed | BenchLeader | 177 tok/s | 59 tok/s |
| Time to first answer | BenchLeader | 11.0 s | 119.6 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,000,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 94.1% | 92.7%† |
| Arena Hard Prompts | Arena (LMArena) | 1501 | 1507 |
| LiveBench 2.0 Reasoning | LiveBench | – | 88.2% |
| LiveBench 1.0 Reasoning | LiveBench | 85.2% | 88.2% |
| GPQA Diamond (AA) | Artificial Analysis | 92.8% | 92.8% |
| Humanity's Last Exam (AA) | Artificial Analysis | 40.8% | 43.1% |
| HLE-Diamond (AA) | Artificial Analysis | – | 24.0% |
| GPQA Diamond (Vals) | Vals AI | 93.4% | 93.7% |
| ARC-AGI-1 | ARC Prize | 91.2% | – |
| ARC-AGI-2 | ARC Prize | 60.4% | – |
| CritPt | Artificial Analysis | 10.6% | 20.0% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 29.5% |
| MysteryMechanism | Vals AI | – | 23.9% |
| Arena Expert | Arena (LMArena) | 1500 | 1514 |
| Chess Puzzles | Epoch AI Benchmarking Hub | 40.0% | 46.0%† |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 30.0% | 38.0%† |
| LMCA | Epoch AI Benchmarking Hub | 44.9% | 46.2%† |
| DTBench | Epoch AI Benchmarking Hub | 95.5% | 92.0%† |
| ForecastBench | ForecastBench | 65.7%† | – |
| Coding | |||
| SciCode | SciCode | 53.4% | 53.2% |
| WeirdML | WeirdML | 56.1% | – |
| FrontierCode | Cognition | 34.4%† | – |
| Arena Coding | Arena (LMArena) | 1518 | 1523 |
| Arena WebDev | Arena (LMArena) | 1538 | 1676 |
| LiveBench 2.0 Coding | LiveBench | – | 60.9% |
Show all 148 benchmarks
| Metric | Publisher | Gemini 3.6 Flash (high) | Qwen3.8 Max (max) |
|---|---|---|---|
| Coding | |||
| LiveBench 1.0 Coding | LiveBench | 77.9% | 72.9% |
| LiveCodeBench | Vals AI | 88.1% | 87.8% |
| IOI | Vals AI | 35.1% | 68.9% |
| SWE-bench (Vals) | Vals AI | 79.6% | 85.6% |
| Code Migration | Vals AI | 30.9% | 24.0% |
| ProgramBench | Vals AI | 0.0% | 0.0% |
| SWE-bench Multimodal | Vals AI | – | 42.5% |
| Vibe Code Bench 1-100 | Vals AI | – | 12.8% |
| Vibe Code Bench v1.1 | Vals AI | 64.0% | 64.7% |
| SWE Atlas v1.1 | Scale AI SEAL | – | 64.4% |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | – | 81.5% |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | – | 58.9% |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | – | 52.9% |
| MirrorCode | Epoch AI Benchmarking Hub | 23.3% | 52.2%† |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 46.7% | 57.5%† |
| ALE-Bench | Epoch AI Benchmarking Hub | 715.5 | 1679.1† |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 17.8%† |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 7.1% | 38.9% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 77.5% | 88.8% |
| Startrise Frontend | Startrise | – | 71.3% |
| GameBench 2 Overall | DuelLab GameBench 2 | 50.6† | 54.2† |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 63.0 | 69.6† |
| Design Arena Website | Design Arena | 1292† | 1269 |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 43.2% |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 23.4% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 27.0% |
| APEX-Agents | Mercor | 46.9%† | 63.3% |
| Arena Agent | Arena (LMArena) | – | 0.1 |
| LiveBench Long Agentic | LiveBench | – | 26.6% |
| LiveBench Browser | LiveBench | – | 49.4% |
| LiveBench Agentic Coding | LiveBench | 43.4% | 64.7% |
| Terminal-Bench 2.1 (Vals) | Vals AI | 73.8% | 67.4% |
| τ³-bench Banking | τ²-bench | – | 55.1%† |
| GDPval-AA v2.1, normalised score | Artificial Analysis | – | 58.3% |
| GDPval-AA v2.1 | Artificial Analysis | 1293 | 1674 |
| τ³-Banking (AA) | Artificial Analysis | 29.9% | 51.3% |
| ITBench SRE (AA) | Artificial Analysis | – | 40.3% |
| Analyst Agent (AA) | Artificial Analysis | – | 45.0% |
| APEX-Agents (AA) | Artificial Analysis | – | 42.4% |
| CyberBench | Vals AI | 45.4% | 28.6% |
| Finance Agent v2 | Vals AI | 56.3% | 50.6% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 3.3% | 10.4% |
| Legal Research Bench | Vals AI | 25.0% | 47.6% |
| SkillsBench | Vals AI | – | 42.0% |
| Tax Agent Bench | Vals AI | 18.0% | 32.1% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 34.3% |
| Terminal-Bench Science | Vals AI | 4.3% | 12.9% |
| Arena Search | Arena (LMArena) | – | 1227 |
| Arena Agent Task Completion | Arena (LMArena) | – | 4.5 |
| AutomationBench | Artificial Analysis | 53.0% | 56.2% |
| GDP.pdf (AA) | Artificial Analysis | 17.4% | 22.8% |
| EnterpriseOps-Gym | Artificial Analysis | – | 47.6% |
| AA-Briefcase v1.1 | Artificial Analysis | 957 | 1604 |
| GDPx | GDPx by SemiAnalysis | – | 3.5% |
| Design Arena Agentic | Design Arena | 1177† | 1264 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 11.9% |
| MKA (AA) | Artificial Analysis | – | 37.4% |
| FACTS Search | 75.7%† | 85.0% | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 59.0% | 74.7%† |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 21.9% | 46.3%† |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 94.2% | 100.0%† |
| ProofBench | Vals AI | 36.0%† | 58.0% |
| LiveBench Mathematics | LiveBench | 86.4% | 91.3% |
| AIME 2026 | MathArena | 96.7%† | – |
| HMMT February 2026 | MathArena | 89.4%† | – |
| MathArena Apex | MathArena | 26.0%† | – |
| Arena Maths | Arena (LMArena) | 1501 | 1505 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 66.2% | 47.3%† |
| LiveBench 2.0 Data Analysis | LiveBench | – | 78.4% |
| LiveBench Research | LiveBench | – | 72.8% |
| LiveBench 1.0 Data Analysis | LiveBench | 63.0% | 78.4% |
| AA-Omniscience v1.1 | Artificial Analysis | – | 10.5 |
| MMLU-Pro | Vals AI | 89.3% | 88.6% |
| LegalBench | Vals AI | 86.7% | 83.6% |
| CorpFin | Vals AI | 63.3% | 65.8% |
| TaxEval | Vals AI | 74.9% | 75.5% |
| BioMysteryBench | Vals AI | 58.5% | – |
| Excel Modeling Benchmark | Vals AI | 65.4% | 60.1% |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 66.0% |
| MedCode | Vals AI | 53.1% | 40.7% |
| MedScribe | Vals AI | 79.7% | 85.0% |
| Public Benefits Bench v1.1 | Vals AI | 56.6% | 67.1% |
| Access to Justice Benchmark | Vals AI | – | 76.4% |
| Financial Coaching Bench | Vals AI | 65.8% | 75.6% |
| Immigration Bench | Vals AI | – | 70.1% |
| GDP.pdf | Epoch AI Benchmarking Hub | 14.0% | 23.2%† |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 29.5% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 72.9% |
| FACTS Parametric | 73.9%† | 30.8% | |
| Instruction following | |||
| LiveBench Language | LiveBench | 83.9% | 79.7% |
| LiveBench Instruction Following | LiveBench | 75.4% | 74.1% |
| Arena Instruction Following | Arena (LMArena) | 1473 | 1478 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1483 | 1484 |
| EQ-Bench Creative Writing v3 | EQ-Bench | 1602† | – |
| Arena Creative Writing | Arena (LMArena) | 1471 | 1472 |
| Arena Multi-turn | Arena (LMArena) | 1490 | 1495 |
| Arena Longer Queries | Arena (LMArena) | 1485 | 1496 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1297 | 1312 |
| LiveBench Design | LiveBench | – | 76.6% |
| MMMU-Pro | Artificial Analysis | 83.2% | 82.8% |
| MMMU-Pro (Vals) | Vals AI | 88.4% | 88.0% |
| MortgageTax | Vals AI | 67.6% | 64.0% |
| SAGE | Vals AI | – | 81.8% |
| Humanity's Sixth Sense | Scale AI SEAL | 31.9% | 33.0% |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 31.2%† | – |
| Furniture Assembly | Epoch AI Benchmarking Hub | 23.3% | 20.0%† |
| VIALS-AA | Handshake AI | – | 31.7% |
| Code2Video-AA | Artificial Analysis | – | 1021 |
| AA-3D | Artificial Analysis | – | 954 |
| FACTS Multimodal | 53.7%† | 51.5% | |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 80.0% | 80.3% |
| Arena Document | Arena (LMArena) | 1454 | – |
| MLCR | Artificial Analysis | 10.0% | 26.1% |
| FACTS Grounding | 66.6%† | 73.8% | |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 155.2† | 157.6 |
| LiveBench 2.0 | LiveBench | – | 60.9% |
| LiveBench 1.0 | LiveBench | 73.6% | 78.5% |
| AA Intelligence Index v5.0.1 | Artificial Analysis | – | 33.6 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 34.0 | 45.4 |
| AA Progress Index v1 | Artificial Analysis | 305.7 | 323.7 |
| Vals RSI Index | Vals AI | – | 21.8% |
| Vals Multimodal Index | Vals AI | 65.1% | 65.4% |
| Safety & honesty | |||
| DistressBench | Scale AI SEAL | – | 77.6% |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Gemini 3.6 Flash: list price moves to $1.50 / $7.50 per 1M input / output tokens (announced).
- Qwen3.8 Max (max): 1 score revision.
- Gemini 3.6 Flash (high): 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1); 1 score revision.
- Qwen3.8 Max (max): 1 score revision.
- Gemini 3.6 Flash (high): 1 new result (MirrorCode); 1 score revision.
- Qwen3.8 Max (max): 6 score revisions.
- Qwen3.8 Max (max): 1 score revision.
- Qwen3.8 Max (max): 1 new result (FACTS Search); 1 score revision.
- Gemini 3.6 Flash (high): 1 score revision.
- Qwen3.8 Max (max): 1 score revision; cached input price moved from $0.22/M to $0.25/M (13% up).
Related comparisons
- Gemini 3.6 Flash vs Gemini 4 Carbon
- Gemini 3.6 Flash vs Claude Opus 5.5
- Qwen3.8 Max vs GPT-6 Astra
- Gemini 3.6 Flash vs GPT-6.1 Sol
- Gemini 3.6 Flash vs Claude Sonnet 5.5
- Gemini 3.6 Flash vs GPT-6.1 Terra
- Gemini 3.6 Flash vs Gemini 3.7 Flash
- Gemini 3.6 Flash vs Kimi K3.1 Pro
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Gemini 3.6 Flash vs Qwen3.8 Max: questions
- Is Gemini 3.6 Flash better than Qwen3.8 Max?
- Gemini 3.6 Flash (high) and Qwen3.8 Max (max) are neck and neck on quality (61.0 vs 58.7, within the ±4.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
- Gemini 3.6 Flash vs Qwen3.8 Max: which is cheaper, and will that change?
- Gemini 3.6 Flash is cheaper today: $1.50 against $3.00 per million tokens, blended at three input tokens per output token. Gemini 3.6 Flash's current price runs until 31 Dec 2026, then $3.00.
- Is Gemini 3.6 Flash or Qwen3.8 Max better for coding?
- Qwen3.8 Max scores higher in coding (62 vs 57 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1538 for Gemini 3.6 Flash against 1676 for Qwen3.8 Max.
- Which is faster, Gemini 3.6 Flash or Qwen3.8 Max?
- Gemini 3.6 Flash streams 3×+ faster (177 vs 59 output tokens per second, Artificial Analysis 7-day median).
- Is Gemini 3.6 Flash or Qwen3.8 Max better for agents and tool use?
- They are level in agentic tasks (59 vs 59 on the category index). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 29.9% for Gemini 3.6 Flash against 51.3% for Qwen3.8 Max.
More questions (4)
- Which is better for long documents?
- They are level on long-context benchmarks (65 vs 65). Both take about 1M tokens: Gemini 3.6 Flash 1,048,576, Qwen3.8 Max 1,000,000.
- Which has lower latency?
- Gemini 3.6 Flash answers first: 11.0 s against 119.6 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Do independent benchmarks agree on Gemini 3.6 Flash vs Qwen3.8 Max?
- Across the 60 benchmarks both have, Gemini 3.6 Flash leads 16, Qwen3.8 Max leads 42 and 2 are tied. Every overall index that rates both puts Qwen3.8 Max ahead.
- When was Qwen3.8 Max released?
- Qwen3.8 Max was released on 3 Aug 2026.