---
title: "Is DeepSeek V3 still undominated? · Undominated.ai"
canonical: https://undominated.ai/check/deepseek__deepseek-chat/
description: "DeepSeek V3: whether it is still undominated. If anything in this catalogue has a higher score or a lower price with neither dimension worse, it is named, as of Nov 22, 2026. Unrated stays unrated."
---

# Is DeepSeek V3 still undominated? · Undominated.ai

> DeepSeek V3: whether it is still undominated. If anything in this catalogue has a higher score or a lower price with neither dimension worse, it is named, as of Nov 22, 2026. Unrated stays unrated.

# Is DeepSeek V3 a good deal?

Whether anything in this catalogue beats DeepSeek V3 on both quality and price, and what you give up if it does. A computation on the current catalogue, not an opinion.

12 undominated of 144 · Nov 22, 2026

 [1 · Choose & set workload](#check-input)[2 · Read verdict](#check-verdict)[3 · Inspect alternatives](#check-options)

As of Nov 22, 2026, DeepSeek V3 is dominated for Balanced on LMArena. GLM 5.3 Flash scores 138.9 higher and costs 70% less, with a covering envelope. 12 of 144 rated, priced standard models are undominated.

[Inspect model evidence](/models/deepseek__deepseek-chat/) [Compare differences & requirements](/compare/?models=deepseek%2Fdeepseek-chat%2Cz-ai%2Fglm-5.3-flash)

 Current model

DeepSeek V3

 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 DeepSeek V3: 138.9 points higher on LMArena and 70% less per million tokens, $0.352 cheaper at this mix.

 [DeepSeek V3](https://undominated.ai/models/deepseek__deepseek-chat/)

LMArena Elo · higher is better

Scale starts at 1040 Elo

 **

1332.5

Effective $/M · Balanced · lower is better

 **

$0.500/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

 **

1471.4

Effective $/M · Balanced · lower is better

 **

$0.148/M

DeepSeek V3 takes text, returns up to 16,000 tokens from a 163,840-token context, and is listed by 3 sellers.

Compared against 144 rated, priced models on this lens: 25 models dominate it and give up nothing, 5 more dominate it but give something up. DeepSeek V3 scores 1332.5 at $0.500 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/) | 1471.4 +138.9 | $0.148/M | 70% |
| [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) | 1463.0 +130.5 | $0.227/M | 55% |
| [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) | 1449.8 +117.3 | $0.175/M | 65% |
| [Gemma 4 31B](/models/google__gemma-4-31b-it/) | 1442.5 +110.0 | $0.205/M | 59% |
| [Hy3](/models/tencent__hy3/) | 1439.0 +106.5 | $0.231/M | 54% |
| [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) | 1434.2 +101.7 | $0.123/M | 75% |
| [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) | 1431.9 +99.4 | $0.113/M | 78% |
| [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) | 1430.9 +98.4 | $0.450/M | 10% |
| [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) | 1424.6 +92.1 | $0.394/M | 21% |
| [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) | 1422.3 +89.8 | $0.305/M | 39% |
| [Qwen3 VL 235B A22B Instruct](/models/qwen__qwen3-vl-235b-a22b-instruct/) | 1420.0 +87.5 | $0.370/M | 26% |
| [DeepSeek V3.1](/models/deepseek__deepseek-chat-v3.1/) | 1419.8 +87.3 | $0.453/M | 10% |
| [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) | 1419.2 +86.7 | $0.205/M | 59% |
| [DeepSeek V3.1 Terminus](/models/deepseek__deepseek-v3.1-terminus/) | 1417.3 +84.8 | $0.453/M | 10% |
| [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) | 1417.2 +84.7 | $0.343/M | 32% |
| [Inkling 2 Small](/models/thinkingmachines__inkling-2-small/) | 1402.6 +70.1 | $0.475/M | 5% |
| [Claude Haiku 5.5](/models/anthropic__claude-haiku-5.5/) | 1397.5 +65.0 | $0.200/M | 60% |
| [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) | 1397.1 +64.6 | $0.114/M | 77% |
| [Qwen3.5-35B-A3B](/models/qwen__qwen3.5-35b-a3b/) | 1394.8 +62.3 | $0.355/M | 29% |
| [GPT-6 Luna](/models/openai__gpt-6-luna/) | 1390.2 +57.7 | $0.200/M | 60% |
| [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) | 1383.7 +51.2 | $0.143/M | 72% |
| [DeepSeek V3 0324](/models/deepseek__deepseek-chat-v3-0324/) | 1374.6 +42.1 | $0.438/M | 13% |
| [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) | 1371.8 +39.3 | $0.463/M | 8% |
| [MiniMax M2.5](/models/minimax__minimax-m2.5/) | 1359.2 +26.7 | $0.440/M | 12% |
| [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) | 1350.7 +18.2 | $0.145/M Price under confirmation since Nov 21, 2026 | 71% |

## 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 4.5 Air](/models/z-ai__glm-4.5-air/) | 1383.7 | $0.310/M | context |
| [GLM 4.6V](/models/z-ai__glm-4.6v/) | 1376.4 | $0.450/M | context |
| [gpt-oss-120b](/models/openai__gpt-oss-120b/) | 1365.4 | $0.060/M | context |
| [Gemma 3 27B](/models/google__gemma-3-27b-it/) | 1357.8 | $0.100/M | context |
| [Qwen3 32B](/models/qwen__qwen3-32b/) | 1340.1 | $0.248/M | context |

 144 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/)
