--- title: "Is R1 still undominated? · Undominated.ai" canonical: https://undominated.ai/check/deepseek__deepseek-r1/ description: "R1: 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 R1 still undominated? · Undominated.ai > R1: 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 R1 a good deal? Whether anything in this catalogue beats R1 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, R1 is dominated for Balanced on LMArena. GLM 5.3 Flash scores 99.3 higher and costs 79% less, with a covering envelope. 13 of 136 rated, priced standard models are undominated. [Inspect model evidence](/models/deepseek__deepseek-r1/) [Compare differences & requirements](/compare/?models=deepseek%2Fdeepseek-r1%2Cz-ai%2Fglm-5.3-flash) Current model R1 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) GLM 5.3 Flash is both better and cheaper than R1: 99.3 points higher on LMArena and 79% less per million tokens, $0.91 cheaper at this mix. [R1](https://undominated.ai/models/deepseek__deepseek-r1/) LMArena Elo · higher is better Scale starts at 1040 Elo ** 1372.6 Effective $/M · Balanced · lower is better ** $1.15/M [GLM 5.3 Flash](https://undominated.ai/models/z-ai__glm-5.3-flash/) LMArena Elo · higher is better Scale starts at 1040 Elo ** 1471.9 Effective $/M · Balanced · lower is better ** $0.237/M R1 takes text, returns up to 16,000 tokens from a 64,000-token context, and is listed by 1 seller. Compared against 136 rated, priced models on this lens: 39 models dominate it and give up nothing, 5 more dominate it but give something up. R1 scores 1372.6 at $1.15 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 | | --- | --- | --- | --- | | [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) | 1471.9 +99.3 | $0.237/M | 79% | | [GLM 5.2](/models/z-ai__glm-5.2/) | 1466.9 +94.3 | $0.998/M | 13% | | [MiMo-V2.5-Pro](/models/xiaomi__mimo-v2.5-pro/) | 1464.8 +92.2 | $0.544/M | 53% | | [Qwen3.7 Plus](/models/qwen__qwen3.7-plus/) | 1454.2 +81.6 | $0.560/M | 51% | | [GLM 5](/models/z-ai__glm-5/) | 1446.3 +73.7 | $0.930/M | 19% | | [Kimi K2.5](/models/moonshotai__kimi-k2.5/) | 1445.6 +73.0 | $0.900/M | 22% | | [Gemma 4 31B](/models/google__gemma-4-31b-it/) | 1441.7 +69.1 | $0.153/M | 87% | | [Hy3](/models/tencent__hy3/) | 1440.6 +68.0 | $0.144/M | 87% | | [GLM 4.6](/models/z-ai__glm-4.6/) | 1440.5 +67.9 | $0.760/M | 34% | | [Qwen3.8 27B](/models/qwen__qwen3.8-27b/) | 1439.3 +66.7 | $1.06/M | 7% | | [Qwen3.6 Plus](/models/qwen__qwen3.6-plus/) | 1436.7 +64.1 | $0.731/M | 36% | | [GLM 4.7](/models/z-ai__glm-4.7/) | 1435.9 +63.3 | $0.738/M | 36% | | [Gemini 3.5 Flash Lite](/models/google__gemini-3.5-flash-lite/) | 1435.5 +62.9 | $0.850/M | 26% | | [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) | 1434.5 +61.9 | $0.143/M | 88% | | [MiniMax M3](/models/minimax__minimax-m3/) | 1433.5 +60.9 | $0.525/M | 54% | | [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) | 1431.8 +59.2 | $0.103/M | 91% | | [GLM 4.5](/models/z-ai__glm-4.5/) | 1430.2 +57.6 | $1.00/M | 13% | | [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) | 1429.9 +57.3 | $0.450/M | 61% | | [R1 0528](/models/deepseek__deepseek-r1-0528/) | 1427.5 +54.9 | $0.912/M | 21% | | [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) | 1427.4 +54.8 | $0.175/M | 85% | | [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) | 1424.8 +52.2 | $0.302/M | 74% | | [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) | 1422.6 +50.0 | $0.305/M | 73% | | [DeepSeek V3.1](/models/deepseek__deepseek-chat-v3.1/) | 1419.7 +47.1 | $0.425/M | 63% | | [Qwen3.5-122B-A10B](/models/qwen__qwen3.5-122b-a10b/) | 1417.9 +45.3 | $0.715/M | 38% | | [Gemini 2.5 Flash](/models/google__gemini-2.5-flash/) | 1417.3 +44.7 | $0.850/M | 26% | | [DeepSeek V3.1 Terminus](/models/deepseek__deepseek-v3.1-terminus/) | 1416.9 +44.3 | $0.453/M | 61% | | [Gemini 3.1 Flash Lite Preview](/models/google__gemini-3.1-flash-lite-preview/) | 1415.3 +42.7 | $0.563/M | 51% | | [Qwen3 235B A22B Thinking 2507](/models/qwen__qwen3-235b-a22b-thinking-2507/) | 1415.1 +42.5 | $0.747/M | 35% | | [Inkling Small](/models/thinkingmachines__inkling-small/) | 1412.3 +39.7 | $0.637/M | 45% | | [Qwen3.5-27B](/models/qwen__qwen3.5-27b/) | 1408.1 +35.5 | $0.536/M | 53% | | [MiniMax M2.7](/models/minimax__minimax-m2.7/) | 1404.6 +32.0 | $0.525/M | 54% | | [Step 3.5 Flash](/models/stepfun__step-3.5-flash/) | 1403.7 +31.1 | $0.150/M | 87% | | [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) | 1397.7 +25.1 | $0.114/M | 90% | | [Qwen3.5-35B-A3B](/models/qwen__qwen3.5-35b-a3b/) | 1395.5 +22.9 | $0.547/M | 52% | | [GLM 4.5 Air](/models/z-ai__glm-4.5-air/) | 1383.7 +11.1 | $0.310/M | 73% | | [Solar Pro 4](/models/upstage__solar-pro4/) | 1377.3 +4.7 | $0.158/M | 86% | | [GLM 4.6V](/models/z-ai__glm-4.6v/) | 1376.5 +3.9 | $0.450/M | 61% | | [GPT-5 Mini](/models/openai__gpt-5-mini/) | 1373.0 +0.4 | $0.688/M | 40% | | [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) | 1372.9 +0.3 | $0.463/M | 60% | ## 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 | | --- | --- | --- | --- | | [Qwen3 VL 235B A22B Instruct](/models/qwen__qwen3-vl-235b-a22b-instruct/) | 1420.6 | $0.632/M | reasoning | | [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) | 1419.8 | $0.153/M | reasoning | | [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) | 1417.6 | $0.343/M | reasoning | | [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) | 1383.6 | $0.084/M | reasoning | | [DeepSeek V3 0324](/models/deepseek__deepseek-chat-v3-0324/) | 1375.0 | $0.438/M | reasoning | 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/)