--- title: "Is Qwen3 Max still undominated? · Undominated.ai" canonical: https://undominated.ai/check/qwen__qwen3-max/ description: "Qwen3 Max: whether it is still undominated. If anything in this catalogue is both better and cheaper, it is named, as of Sep 23, 2026. Unrated stays unrated." --- # Is Qwen3 Max still undominated? · Undominated.ai > Qwen3 Max: whether it is still undominated. If anything in this catalogue is both better and cheaper, it is named, as of Sep 23, 2026. Unrated stays unrated. # Is Qwen3 Max a good deal? Whether anything in this catalogue beats Qwen3 Max on both quality and price, and what you give up if it does. A computation on the current catalogue, not an opinion. 13 undominated of 136 · Sep 23, 2026 [1 · Choose & set workload](#check-input)[2 · Read verdict](#check-verdict)[3 · Inspect alternatives](#check-options) As of Sep 23, 2026, Qwen3 Max is dominated for Balanced on LMArena. Gemini 3.8 Flash scores 81.6 higher and costs 4% less, with a covering envelope. 13 of 136 rated, priced standard models are undominated. [Inspect model evidence](/models/qwen__qwen3-max/) [Compare differences & requirements](/compare/?models=qwen%2Fqwen3-max%2Cgoogle%2Fgemini-3.8-flash) Current model Qwen3 Max Balanced 3 tokens in per 1 out Balanced Summarise Chat Code gen Agentic Monthly spend (USD) Used only to say how many months a named switching cost would take to earn back. Leave blank to skip. Switching cost (USD) Gemini 3.8 Flash is both better and cheaper than Qwen3 Max: 81.6 points higher on LMArena and 4% less per million tokens, $0.06 cheaper at this mix. [Qwen3 Max](https://undominated.ai/models/qwen__qwen3-max/) LMArena Elo · higher is better Scale starts at 1040 Elo ** 1413.1 Effective $/M · Balanced · lower is better ** $1.56/M [Gemini 3.8 Flash](https://undominated.ai/models/google__gemini-3.8-flash/) LMArena Elo · higher is better Scale starts at 1040 Elo ** 1494.7 Effective $/M · Balanced · lower is better ** $1.50/M Qwen3 Max takes text, returns up to 65,536 tokens from a 262,144-token context, and is listed by 1 seller. Compared against 136 rated, priced models on this lens: 22 models dominate it and give up nothing, 5 more dominate it but give something up. Qwen3 Max scores 1413.1 at $1.56 per million tokens for this mix. ## Envelope-safe replacements Each row scores at least as high, costs no more, and covers this model’s context, output, modalities, tools, and reasoning. A cheaper narrower model is not listed here. | Model | LMArena | Effective $/M | You save | | --- | --- | --- | --- | | [Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) | 1494.7 +81.6 | $1.50/M | 4% | | [Gemini 3.7 Flash](/models/google__gemini-3.7-flash/) | 1490.5 +77.4 | $1.50/M | 4% | | [Gemini 3.6 Flash](/models/google__gemini-3.6-flash/) | 1476.1 +63.0 | $1.50/M | 4% | | [GLM 5.3](/models/z-ai__glm-5.3/) | 1475.1 +62.0 | $1.29/M | 17% | | [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) | 1471.9 +58.8 | $0.237/M | 85% | | [GLM 5.2](/models/z-ai__glm-5.2/) | 1466.9 +53.8 | $0.998/M | 36% | | [MiMo-V2.5-Pro](/models/xiaomi__mimo-v2.5-pro/) | 1464.8 +51.7 | $0.544/M | 65% | | [Qwen3.7 Plus](/models/qwen__qwen3.7-plus/) | 1454.2 +41.1 | $0.560/M | 64% | | [Kimi K2.5](/models/moonshotai__kimi-k2.5/) | 1445.6 +32.5 | $0.900/M | 42% | | [DeepSeek V4 Pro 0423](/models/deepseek__deepseek-v4-pro/) | 1444.0 +30.9 | $1.18/M | 24% | | [Hy3](/models/tencent__hy3/) | 1440.6 +27.5 | $0.144/M | 91% | | [Qwen3.8 27B](/models/qwen__qwen3.8-27b/) | 1439.3 +26.2 | $1.06/M | 32% | | [Qwen3.5 397B A17B](/models/qwen__qwen3.5-397b-a17b/) | 1438.3 +25.2 | $1.29/M | 17% | | [Qwen3.6 Plus](/models/qwen__qwen3.6-plus/) | 1436.7 +23.6 | $0.731/M | 53% | | [Gemini 3.5 Flash Lite](/models/google__gemini-3.5-flash-lite/) | 1435.5 +22.4 | $0.850/M | 46% | | [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) | 1434.5 +21.4 | $0.143/M | 91% | | [MiniMax M3](/models/minimax__minimax-m3/) | 1433.5 +20.4 | $0.525/M | 66% | | [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) | 1431.8 +18.7 | $0.103/M | 93% | | [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) | 1429.9 +16.8 | $0.450/M | 71% | | [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) | 1427.4 +14.3 | $0.175/M | 89% | | [Qwen3.5-122B-A10B](/models/qwen__qwen3.5-122b-a10b/) | 1417.9 +4.8 | $0.715/M | 54% | | [Gemini 3.1 Flash Lite Preview](/models/google__gemini-3.1-flash-lite-preview/) | 1415.3 +2.2 | $0.563/M | 64% | ## Higher score, lower price, named losses Not a drop-in. The loss is why these are not a recommendation. | Model | LMArena | Effective $/M | You give up | | --- | --- | --- | --- | | [GLM 5.1](/models/z-ai__glm-5.1/) | 1462.4 | $1.48/M | context | | [GLM 5](/models/z-ai__glm-5/) | 1446.3 | $0.930/M | context | | [Gemma 4 31B](/models/google__gemma-4-31b-it/) | 1441.7 | $0.153/M | max output | | [GLM 4.6](/models/z-ai__glm-4.6/) | 1440.5 | $0.760/M | context, max output | | [GLM 4.7](/models/z-ai__glm-4.7/) | 1435.9 | $0.738/M | context | 136 rated, priced standard models. Chartreuse is the frontier. Cobalt is the model you named, when it is not on the staircase. Copy watch URL [Open the frontier](/frontier/) The link keeps the model and mix, using the current catalogue. Monthly spend and switching cost stay in this browser tab and are left out of the link. ## Saved decision references Save the model, workload, catalogue date and capability-preservation rule in this browser. Spend, switching cost and bill contents are not saved. No account or notifications. Constraint: replacements must preserve the model’s capabilities; any losses remain named trade-offs. Historical decisions cannot be fully replayed from saved references: past prices, scores and capability evidence are not stored. Save this reference ## Continue your investigation - [Build a shortlist](/compare/) - [Inspect alternatives](/alternatives/) - [Check billing conditions](/traps/) - [Read model evidence](/models/)