---
title: "Is Qwen2.5 72B Instruct still undominated? · Undominated.ai"
canonical: https://undominated.ai/check/qwen__qwen-2.5-72b-instruct/
description: "Qwen2.5 72B Instruct: 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 Qwen2.5 72B Instruct still undominated? · Undominated.ai

> Qwen2.5 72B Instruct: 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 Qwen2.5 72B Instruct a good deal?

Whether anything in this catalogue beats Qwen2.5 72B Instruct 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, Qwen2.5 72B Instruct is dominated for Balanced on LMArena. GLM 5.3 Flash scores 202.3 higher and costs 60% less, with a covering envelope. 12 of 144 rated, priced standard models are undominated.

[Inspect model evidence](/models/qwen__qwen-2.5-72b-instruct/) [Compare differences & requirements](/compare/?models=qwen%2Fqwen-2.5-72b-instruct%2Cz-ai%2Fglm-5.3-flash)

 Current model

Qwen2.5 72B Instruct

 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 Qwen2.5 72B Instruct: 202.3 points higher on LMArena and 60% less per million tokens, $0.222 cheaper at this mix.

 [Qwen2.5 72B Instruct](https://undominated.ai/models/qwen__qwen-2.5-72b-instruct/)

LMArena Elo · higher is better

Scale starts at 1040 Elo

 **

1269.1

Effective $/M · Balanced · lower is better

 **

$0.370/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

Qwen2.5 72B Instruct takes text, returns up to 16,384 tokens from a 32,768-token context, and is listed by 2 sellers.

Compared against 144 rated, priced models on this lens: 29 models dominate it and give up nothing, 1 more dominates it but gives something up. Qwen2.5 72B Instruct scores 1269.1 at $0.370 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 +202.3 | $0.148/M | 60% |
| [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) | 1463.0 +193.9 | $0.227/M | 39% |
| [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) | 1449.8 +180.7 | $0.175/M | 53% |
| [Gemma 4 31B](/models/google__gemma-4-31b-it/) | 1442.5 +173.4 | $0.205/M | 45% |
| [Hy3](/models/tencent__hy3/) | 1439.0 +169.9 | $0.231/M | 38% |
| [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) | 1434.2 +165.1 | $0.123/M | 67% |
| [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) | 1431.9 +162.8 | $0.113/M | 70% |
| [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) | 1422.3 +153.2 | $0.305/M | 18% |
| [Qwen3 VL 235B A22B Instruct](/models/qwen__qwen3-vl-235b-a22b-instruct/) | 1420.0 +150.9 | $0.370/M | 0% |
| [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) | 1419.2 +150.1 | $0.205/M | 45% |
| [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) | 1417.2 +148.1 | $0.343/M | 7% |
| [Claude Haiku 5.5](/models/anthropic__claude-haiku-5.5/) | 1397.5 +128.4 | $0.200/M | 46% |
| [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) | 1397.1 +128.0 | $0.114/M | 69% |
| [Qwen3.5-35B-A3B](/models/qwen__qwen3.5-35b-a3b/) | 1394.8 +125.7 | $0.355/M | 4% |
| [GPT-6 Luna](/models/openai__gpt-6-luna/) | 1390.2 +121.1 | $0.200/M | 46% |
| [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) | 1383.7 +114.6 | $0.143/M | 61% |
| [GLM 4.5 Air](/models/z-ai__glm-4.5-air/) | 1383.7 +114.6 | $0.310/M | 16% |
| [gpt-oss-120b](/models/openai__gpt-oss-120b/) | 1365.4 +96.3 | $0.060/M | 84% |
| [Gemma 3 27B](/models/google__gemma-3-27b-it/) | 1357.8 +88.7 | $0.100/M | 73% |
| [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) | 1350.7 +81.6 | $0.145/M Price under confirmation since Nov 21, 2026 | 61% |
| [Qwen3 32B](/models/qwen__qwen3-32b/) | 1340.1 +71.0 | $0.248/M | 33% |
| [Gemma 3 12B](/models/google__gemma-3-12b-it/) | 1334.2 +65.1 | $0.075/M | 80% |
| [GPT-5 Nano](/models/openai__gpt-5-nano/) | 1320.0 +50.9 | $0.138/M | 63% |
| [Granite 4.2 8B](/models/ibm-granite__granite-4.2-8b/) | 1318.8 +49.7 | $0.083/M | 78% |
| [Qwen3 30B A3B](/models/qwen__qwen3-30b-a3b/) | 1316.8 +47.7 | $0.215/M | 42% |
| [gpt-oss-20b](/models/openai__gpt-oss-20b/) | 1287.6 +18.5 | $0.034/M | 91% |
| [GPT-4o-mini (2024-07-18)](/models/openai__gpt-4o-mini-2024-07-18/) | 1286.4 +17.3 | $0.263/M | 29% |
| [GPT-4.1 Nano](/models/openai__gpt-4.1-nano/) | 1284.8 +15.7 | $0.175/M | 53% |
| [Llama 3.3 70B Instruct](/models/meta-llama__llama-3.3-70b-instruct/) | 1274.3 +5.2 | $0.280/M | 24% |

## 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 |
| --- | --- | --- | --- |
| [Gemma 3 4B](/models/google__gemma-3-4b-it/) | 1290.8 | $0.043/M | tools |

 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/)
