---
title: "Compare alternatives to Qwen2.5 72B Instruct · Undominated.ai"
canonical: https://undominated.ai/alternatives/qwen__qwen-2.5-72b-instruct/
description: "60 alternatives score at least as high as Qwen2.5 72B Instruct and cost no more under at least one listed workload. 58 preserve recorded capabilities; 2 have named trade-offs."
---

# Compare alternatives to Qwen2.5 72B Instruct · Undominated.ai

> 60 alternatives score at least as high as Qwen2.5 72B Instruct and cost no more under at least one listed workload. 58 preserve recorded capabilities; 2 have named trade-offs.

# Alternatives to Qwen2.5 72B Instruct

Qwen · LMArena 1269 · $0.370/M on a balanced workload · prices as of 2026-10-06

 [Compare models](https://undominated.ai/compare/) Comparison context

Choose up to three standard models in Compare.

Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls.

## 58 models are higher-scoring or cheaper, with neither dimension worse.

Of the 144 models carrying both an independent score and a published price at the same delivery mode, **60** score at least as high as Qwen2.5 72B Instruct and cost no more under at least one listed workload, with at least one of those dimensions improved. **58** match or beat its recorded context, maximum output, input modes, tool use and extended reasoning. **2** have a recorded capability loss, named on every row.

Dominance is not a property of a model. It is a property of a model, a capability lens and a workload, and all three are named on every row. Scores are LMArena Elo, used under CC BY 4.0 from the official dataset; prices are blended per million tokens. A higher score is not a drop-in replacement.

This page is built only while a candidate improves score or price without worsening the other under a listed workload. When that comparison no longer holds, it is not generated.

## Where it holds

| Workload | Qwen2.5 72B Instruct $/M | Recorded capabilities preserved | Recorded capability losses |
| --- | --- | --- | --- |
| Balanced | $0.370 | 31 | 1 |
| Summarise | $0.362 | 57 | 2 |
| Chat | $0.376 | 28 | 1 |
| Code gen | $0.384 | 26 | 1 |
| Agentic | $0.366 | 48 | 1 |

Workload mixes are defined on the [methodology page](/methodology/). Cached input is priced at the cached rate, and reasoning tokens at the worse of the reasoning and output rates.

## What you would be replacing

| Intelligence | 1269 |
| --- | --- |
| Context window | 32K |
| Max output | 16K |
| Input modes | text |
| Tool use | yes |
| Extended reasoning | no |

Preserving recorded capabilities requires matching or beating these fields. [Full record for Qwen2.5 72B Instruct](/models/qwen__qwen-2.5-72b-instruct/), or [check Qwen2.5 72B Instruct against the whole catalogue](/check/qwen__qwen-2.5-72b-instruct/).

## Recorded capabilities preserved 58

Each option has a higher score or a lower price, with neither dimension worse under the listed workloads. It matches or beats Qwen2.5 72B Instruct on recorded context, maximum output, input modes, tool use and extended reasoning.

| # | Model | Intelligence | $/M | Holds under |
| --- | --- | --- | --- | --- |
| 1 | [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) Z.ai | 1469.6 +200.6 | $0.238 | Balanced −36% Summarise −63% Chat −32% Code gen −9% Agentic −64% |
| 2 | [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) DeepSeek | 1462.5 +193.5 | $0.182 | Balanced −51% Summarise −82% Chat −34% Code gen −6% Agentic −71% |
| 3 | [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) Xiaomi | 1456.4 +187.4 | $0.175 | Balanced −53% Summarise −70% Chat −59% Code gen −45% Agentic −78% |
| 4 | [Gemma 4 31B](/models/google__gemma-4-31b-it/) Google | 1443.4 +174.4 | $0.205 | Balanced −45% Summarise −58% Chat −35% Code gen −23% Agentic −51% |
| 5 | [Hy3](/models/tencent__hy3/) Tencent | 1440.7 +171.7 | $0.231 | Balanced −38% Summarise −66% Chat −31% Code gen −6% Agentic −64% |
| 6 | [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) Google | 1433.9 +164.9 | $0.127 | Balanced −66% Summarise −81% Chat −60% Code gen −47% Agentic −78% |
| 7 | [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) DeepSeek | 1432.1 +163.1 | $0.113 | Balanced −70% Summarise −80% Chat −72% Code gen −64% Agentic −83% |
| 8 | [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) Xiaomi | 1427.5 +158.5 | $0.175 | Balanced −53% Summarise −70% Chat −59% Code gen −45% Agentic −78% |
| 9 | [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) DeepSeek | 1424.5 +155.5 | $0.290 | Balanced −22% Summarise −37% Chat −28% Code gen −16% Agentic −45% |
| 10 | [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) DeepSeek | 1422.4 +153.4 | $0.305 | Balanced −18% Summarise −23% Chat −13% Code gen −8% Agentic −20% |
| 11 | [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) Qwen | 1419.3 +150.3 | $0.205 | Balanced −45% Summarise −69% Chat −27% Code gen −5% Agentic −57% |
| 12 | [Qwen3 VL 235B A22B Instruct](/models/qwen__qwen3-vl-235b-a22b-instruct/) Qwen | 1420.1 +151.1 | $0.370 | Balanced same price Summarise −42% Agentic −32% |
| 13 | [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) Qwen | 1417.3 +148.3 | $0.268 | Balanced −28% Summarise −64% Chat −1% Agentic −45% |
| 14 | [Step 3.5 Flash](/models/stepfun__step-3.5-flash/) StepFun | 1403 +134 | $0.150 | Balanced −59% Summarise −70% Chat −52% Code gen −43% Agentic −64% |
| 15 | [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) Qwen | 1397 +128 | $0.114 | Balanced −69% Summarise −79% Chat −62% Code gen −53% Agentic −74% |
| 16 | [GPT-6 Luna](/models/openai__gpt-6-luna/) OpenAI | 1391.5 +122.5 | $0.200 | Balanced −46% Summarise −74% Chat −38% Code gen −13% Agentic −71% |
| 17 | [Qwen3.5-35B-A3B](/models/qwen__qwen3.5-35b-a3b/) Qwen | 1394.4 +125.4 | $0.355 | Balanced −4% Summarise −57% Agentic −41% |
| 18 | [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) Qwen | 1384.1 +115.1 | $0.143 | Balanced −61% Summarise −72% Chat −54% Code gen −44% Agentic −67% |
| 19 | [GLM 4.5 Air](/models/z-ai__glm-4.5-air/) Z.ai | 1383.9 +114.9 | $0.310 | Balanced −16% Summarise −62% Agentic −52% |
| 20 | [gpt-oss-120b](/models/openai__gpt-oss-120b/) OpenAI | 1365.4 +96.4 | $0.065 | Balanced −82% Summarise −90% Chat −77% Code gen −70% Agentic −86% |
| 21 | [Gemma 3 27B](/models/google__gemma-3-27b-it/) Google | 1357.8 +88.8 | $0.100 | Balanced −73% Summarise −77% Chat −70% Code gen −67% Agentic −75% |
| 22 | [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) Z.ai | 1350.9 +81.9 | $0.145 | Balanced −61% Summarise −83% Chat −52% Code gen −32% Agentic −78% |
| 23 | [Qwen3 32B](/models/qwen__qwen3-32b/) Qwen | 1340.1 +71.1 | $0.130 | Balanced −65% Summarise −75% Chat −57% Code gen −48% Agentic −70% |
| 24 | [Gemma 3 12B](/models/google__gemma-3-12b-it/) Google | 1334.2 +65.2 | $0.075 | Balanced −80% Summarise −85% Chat −76% Code gen −71% Agentic −82% |
| 25 | [GPT-5 Nano](/models/openai__gpt-5-nano/) OpenAI | 1320 +51 | $0.138 | Balanced −63% Summarise −85% Chat −53% Code gen −33% Agentic −79% |
| 26 | [Granite 4.2 8B](/models/ibm-granite__granite-4.2-8b/) IBM | 1317.8 +48.8 | $0.108 | Balanced −71% Summarise −84% Chat −67% Code gen −56% Agentic −83% |
| 27 | [Qwen3 30B A3B](/models/qwen__qwen3-30b-a3b/) Qwen | 1316.6 +47.6 | $0.215 | Balanced −42% Summarise −62% Chat −28% Code gen −9% Agentic −52% |
| 28 | [gpt-oss-20b](/models/openai__gpt-oss-20b/) OpenAI | 1287.7 +18.7 | $0.036 | Balanced −90% Summarise −95% Chat −88% Code gen −84% Agentic −94% |
| 29 | [GPT-4.1 Nano](/models/openai__gpt-4.1-nano/) OpenAI | 1284.8 +15.8 | $0.175 | Balanced −53% Summarise −74% Chat −47% Code gen −29% Agentic −73% |
| 30 | [GPT-4o-mini (2024-07-18)](/models/openai__gpt-4o-mini-2024-07-18/) OpenAI | 1286.4 +17.4 | $0.263 | Balanced −29% Summarise −58% Chat −18% Agentic −53% |
| 31 | [Llama 3.3 70B Instruct](/models/meta-llama__llama-3.3-70b-instruct/) Meta | 1274.1 tie | $0.201 | Balanced −46% Summarise −59% Chat −36% Code gen −23% Agentic −52% |
| 32 | [MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) Xiaomi | 1491 +222 | $0.330 summarise | Summarise −9% Agentic −34% |
| 33 | [GLM 5.3](/models/z-ai__glm-5.3/) Z.ai | 1471.4 +202.4 | $0.346 summarise | Summarise −4% |
| 34 | [MiMo-V2.5-Pro](/models/xiaomi__mimo-v2.5-pro/) Xiaomi | 1465 +196 | $0.334 summarise | Summarise −8% Agentic −33% |
| 35 | [Qwen3.7 Plus](/models/qwen__qwen3.7-plus/) Qwen | 1454.6 +185.6 | $0.295 summarise | Summarise −18% Agentic −15% |
| 36 | [Qwen3.8 27B](/models/qwen__qwen3.8-27b/) Qwen | 1440.7 +171.7 | $0.183 summarise | Summarise −50% |
| 37 | [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) OpenAI | 1431 +162 | $0.199 summarise | Summarise −45% Agentic −34% |
| 38 | [Gemini 3.5 Flash Lite](/models/google__gemini-3.5-flash-lite/) Google | 1434.7 +165.7 | $0.333 summarise | Summarise −8% |
| 39 | [MiniMax M3](/models/minimax__minimax-m3/) MiniMax | 1432.1 +163.1 | $0.257 summarise | Summarise −29% Agentic −26% |
| 40 | [DeepSeek V3.1](/models/deepseek__deepseek-chat-v3.1/) DeepSeek | 1419.7 +150.7 | $0.307 summarise | Summarise −15% |
| 41 | [Gemini 3.1 Flash Lite Preview](/models/google__gemini-3.1-flash-lite-preview/) Google | 1415.7 +146.7 | $0.248 summarise | Summarise −31% Agentic −17% |
| 42 | [DeepSeek V3.1 Terminus](/models/deepseek__deepseek-v3.1-terminus/) DeepSeek | 1417.1 +148.1 | $0.307 summarise | Summarise −15% |
| 43 | [Gemini 2.5 Flash](/models/google__gemini-2.5-flash/) Google | 1417 +148 | $0.333 summarise | Summarise −8% |
| 44 | [Qwen3.5-122B-A10B](/models/qwen__qwen3.5-122b-a10b/) Qwen | 1417.1 +148.1 | $0.351 summarise | Summarise −3% |
| 45 | [Qwen3 235B A22B Thinking 2507](/models/qwen__qwen3-235b-a22b-thinking-2507/) Qwen | 1415.2 +146.2 | $0.334 summarise | Summarise −8% |
| 46 | [Inkling Small](/models/thinkingmachines__inkling-small/) Thinking Machines | 1413.7 +144.7 | $0.354 agentic | Agentic −3% |
| 47 | [Qwen3.5-27B](/models/qwen__qwen3.5-27b/) Qwen | 1408.9 +139.9 | $0.263 summarise | Summarise −27% |
| 48 | [MiniMax M2.7](/models/minimax__minimax-m2.7/) MiniMax | 1404.6 +135.6 | $0.277 summarise | Summarise −24% Agentic −20% |
| 49 | [Solar Pro 4](/models/upstage__solar-pro4/) Upstage | 1386.2 +117.2 | $0.277 summarise | Summarise −24% Agentic −20% |
| 50 | [GLM 4.6V](/models/z-ai__glm-4.6v/) Z.ai | 1376.8 +107.8 | $0.259 summarise | Summarise −29% Agentic −34% |
| 51 | [DeepSeek V3 0324](/models/deepseek__deepseek-chat-v3-0324/) DeepSeek | 1375 +106 | $0.288 summarise | Summarise −21% Agentic −1% |
| 52 | [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) OpenAI | 1372.1 +103.1 | $0.201 summarise | Summarise −44% Agentic −32% |
| 53 | [GPT-5 Mini](/models/openai__gpt-5-mini/) OpenAI | 1373.2 +104.2 | $0.273 summarise | Summarise −24% |
| 54 | [Qwen3 Next 80B A3B Thinking](/models/qwen__qwen3-next-80b-a3b-thinking/) Qwen | 1368.3 +99.3 | $0.203 summarise | Summarise −44% Agentic −16% |
| 55 | [MiniMax M2.5](/models/minimax__minimax-m2.5/) MiniMax | 1359.3 +90.3 | $0.273 summarise | Summarise −25% Agentic −21% |
| 56 | [Mercury 2](/models/inception__mercury-2/) Inception | 1355.2 +86.2 | $0.211 summarise | Summarise −42% Agentic −48% |
| 57 | [Trinity Large Thinking](/models/arcee-ai__trinity-large-thinking/) Arcee | 1340 +71 | $0.223 summarise | Summarise −38% Agentic −40% |
| 58 | [MiniMax M2](/models/minimax__minimax-m2/) MiniMax | 1339.9 +70.9 | $0.268 summarise | Summarise −26% Agentic −25% |

## Alternatives with recorded capability losses 2

These improve score or price without worsening the other under the listed workloads, but reduce at least one recorded capability. Read the last column before switching.

| Model | Intelligence | $/M | Holds under | Recorded capability loss |
| --- | --- | --- | --- | --- |
| [Gemma 3 4B](/models/google__gemma-3-4b-it/) Google | 1290.8 +21.8 | $0.063 | Balanced −83% Summarise −85% Chat −81% Code gen −79% Agentic −84% | no tool use |
| [DeepSeek V3](/models/deepseek__deepseek-chat/) DeepSeek | 1332.5 +63.5 | $0.329 summarise | Summarise −9% | 16K → 16K max output |

## What this compares, and what it leaves out

 - Quality is LMArena Elo, used under CC BY 4.0 from the official dataset. The 95% confidence interval on a difference between two scores is about ±10.47 points, so a gap smaller than that is marked *tie* rather than an improvement — see [significance bands](/significance/).
 - 204 further models at this delivery mode carry a price but no independent score. They are absent from the comparison in both directions — unrated is not a zero, and an unmeasured model is neither an alternative nor a worse buy.
 - Retired models are never offered as an alternative, and a model only competes against its own delivery mode: batch trades latency for price, so it is not a like-for-like swap.
 - Nothing here measures latency, throughput, rate limits or how a model behaves on your prompts. Two models with the same index score are not interchangeable.
 - Models with no higher-scoring or cheaper alternative that is no worse on the other axis are on the [value frontier](/frontier/). Models with such an alternative are [listed here](/alternatives/).

## Continue your investigation

 - [Check requirements](/check/)
- [Compare exact differences](/compare/)
- [Set a quality floor](/cheapest-at/)
- [Inspect tier boundaries](/cliffs/)