# Qwen3 Max > Source: Benchize (https://benchize.com) — https://benchize.com/models/qwen3-max. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/qwen3-max. Alibaba Canonical URL: https://benchize.com/models/qwen3-max Last updated: Thu, 22 Oct 2026 04:30:12 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Alibaba ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Source | | | --- | --- | --- | --- | --- | --- | --- | | [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,128elo | — | 46 / 65 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1128 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported sourceModelVersion qwen3-max variationName public ### Reported statistics averageGenerationTimeMs 76858 battles 305 losses 161 standardError Not reported winRate 47.2 wins 144 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label Qwen3 Max Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/64` | | | | | | | | [τ-bench airline (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Aairline.md) | 59.5% | — | 9 / 14 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/qwen3-max_qwen_2024_09_23/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 59.5 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 55 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 46 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2024-09-23","notes":"Only average results are in the blog post. Evaluation limited to Pass^1, Pass^2 and Pass^4 scores only","tau2_bench_version":"0.1.3","user_simulator":null,"verification":{"details":"Unverified submission - no trajectory data available, unknown evaluation methodology, incomplete evaluation (Pass^1, Pass^2 and Pass^4 only)","modified_prompts":null,"omitted_questions":null}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission qwen3-max_qwen_2024_09_23 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/qwen3-max_qwen_2024_09_23/submission.json) Source sierra Original model label Qwen3-Max Evaluated 2024-09-23 Observed 2026-10-21T16:55:03.034Z Evidence SHA-256 `ebc4a976a9ccf834c06e7035681b8569b3a34b263c4f383da6499db1fbfd2969` Source locator `/results/airline` | | | | | | | | [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,074elo | — | 73 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1074 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion qwen3-max variationName public ### Reported statistics averageGenerationTimeMs 72969 battles 4044 losses 2284 standardError Not reported winRate 43.5 wins 1760 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label Qwen3 Max Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/117` | | | | | | | | [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,094elo | — | 87 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1094 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion qwen3-max variationName public ### Reported statistics averageGenerationTimeMs 121317 battles 4161 losses 2337 standardError Not reported winRate 43.8 wins 1824 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label Qwen3 Max Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/129` | | | | | | | | [τ-bench retail (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Aretail.md) | 72.2% | — | 11 / 14 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/qwen3-max_qwen_2024_09_23/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 72.2 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 67.5 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 57 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2024-09-23","notes":"Only average results are in the blog post. Evaluation limited to Pass^1, Pass^2 and Pass^4 scores only","tau2_bench_version":"0.1.3","user_simulator":null,"verification":{"details":"Unverified submission - no trajectory data available, unknown evaluation methodology, incomplete evaluation (Pass^1, Pass^2 and Pass^4 only)","modified_prompts":null,"omitted_questions":null}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission qwen3-max_qwen_2024_09_23 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/qwen3-max_qwen_2024_09_23/submission.json) Source sierra Original model label Qwen3-Max Evaluated 2024-09-23 Observed 2026-10-21T16:55:03.034Z Evidence SHA-256 `ebc4a976a9ccf834c06e7035681b8569b3a34b263c4f383da6499db1fbfd2969` Source locator `/results/retail` | | | | | | | | [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,078elo | — | 88 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1078 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion qwen3-max variationName public ### Reported statistics averageGenerationTimeMs 93767 battles 1524 losses 911 standardError Not reported winRate 40.2 wins 613 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label Qwen3 Max Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/133` | | | | | | | | [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,011elo | — | 71 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1011 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported sourceModelVersion qwen3-max variationName public ### Reported statistics averageGenerationTimeMs 31443 battles 4182 losses 2625 standardError Not reported winRate 37.2 wins 1557 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label Qwen3 Max Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/113` | | | | | | | | [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,100elo | — | 84 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1100 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion qwen3-max variationName public ### Reported statistics averageGenerationTimeMs 85050 battles 1024 losses 602 standardError Not reported winRate 41.2 wins 422 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label Qwen3 Max Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/123` | | | | | | | | [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,110elo | SE ±2.07 | 90 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1110 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion qwen3-max variationName public ### Reported statistics Uncertainty Standard error: ±2.07 averageGenerationTimeMs 107871 battles 33373 losses 18694 standardError 2.0702 winRate 44 wins 14679 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label Qwen3 Max Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/134` | | | | | | | | [τ-bench telecom (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Atelecom.md) | 84.2% | — | 6 / 10 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/qwen3-max_qwen_2024_09_23/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 84.2 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 77.6 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 61.4 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2024-09-23","notes":"Only average results are in the blog post. Evaluation limited to Pass^1, Pass^2 and Pass^4 scores only","tau2_bench_version":"0.1.3","user_simulator":null,"verification":{"details":"Unverified submission - no trajectory data available, unknown evaluation methodology, incomplete evaluation (Pass^1, Pass^2 and Pass^4 only)","modified_prompts":null,"omitted_questions":null}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission qwen3-max_qwen_2024_09_23 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/qwen3-max_qwen_2024_09_23/submission.json) Source sierra Original model label Qwen3-Max Evaluated 2024-09-23 Observed 2026-10-21T16:55:03.034Z Evidence SHA-256 `ebc4a976a9ccf834c06e7035681b8569b3a34b263c4f383da6499db1fbfd2969` Source locator `/results/telecom` | | | | | | | | [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,478 | — | 75 / 191 | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1478 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_max ### Reported statistics coverageCount 27 draws 4 judged 80 losses 34 rank 102 ratingDeviation 28 wins 42 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3 Max Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/98` | | | | | | | | [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,119elo | — | 92 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1119 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion qwen3-max variationName public ### Reported statistics averageGenerationTimeMs 113606 battles 22620 losses 12560 standardError Not reported winRate 44.5 wins 10060 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label Qwen3 Max Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/137` | | | | | | | | [Vending-Bench 2](https://benchize.com/benchmarks/vendingbench%3Av2.md) | — | — | — | $71.57 | [vendingbench](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `final_balance` \| 71.56500000000018 \| USD \| one_simulated_year \| Higher is better \| \| `geometric_mean_balance` \| 544.1700000000016 \| USD \| positive_final_balances \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Qwen3 Max thinkingEnabled Not reported ### Reported statistics confidenceHalfWidth95 185.2614167546178 positiveBalanceRuns 1 runCount 6 standardDeviation 231.52854085403874 standardError 94.52113099725399 ### Source [Original source](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) Source vendingbench Original model label Qwen3 Max Observed 2026-10-21T16:36:40.592Z Evidence SHA-256 `1a0b043147050298c405bcb743d73e425d532464202231cd18c27f836fa5f223` Source locator `/rows/70` | | | | | | | --- Cite as: Qwen3 Max — Benchize, https://benchize.com/models/qwen3-max (retrieved 2026-10-22)