---
title: "Is Llama 3.1 70B Instruct still undominated? · Undominated.ai"
canonical: https://undominated.ai/check/meta-llama__llama-3.1-70b-instruct/
description: "Llama 3.1 70B 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 Llama 3.1 70B Instruct still undominated? · Undominated.ai

> Llama 3.1 70B 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 Llama 3.1 70B Instruct a good deal?

Whether anything in this catalogue beats Llama 3.1 70B 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, Llama 3.1 70B Instruct is dominated for Balanced on LMArena. MiMo-V2.6-Pro scores 231.8 higher and costs 25% less, with a covering envelope. 12 of 144 rated, priced standard models are undominated.

[Inspect model evidence](/models/meta-llama__llama-3.1-70b-instruct/) [Compare differences & requirements](/compare/?models=meta-llama%2Fllama-3.1-70b-instruct%2Cxiaomi%2Fmimo-v2.6-pro)

 Current model

Llama 3.1 70B 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)

MiMo-V2.6-Pro is both better and cheaper than Llama 3.1 70B Instruct: 231.8 points higher on LMArena and 25% less per million tokens, $0.180 cheaper at this mix.

 [Llama 3.1 70B Instruct](https://undominated.ai/models/meta-llama__llama-3.1-70b-instruct/)

LMArena Elo · higher is better

Scale starts at 1040 Elo

 **

1260.9

Effective $/M · Balanced · lower is better

 **

$0.720/M

 [MiMo-V2.6-Pro](https://undominated.ai/models/xiaomi__mimo-v2.6-pro/)

LMArena Elo · higher is better

Scale starts at 1040 Elo

 **

1492.7

Effective $/M · Balanced · lower is better

 **

$0.540/M

Llama 3.1 70B Instruct takes text, returns up to 8,192 tokens from a 131,072-token context, and is listed by 1 seller.

Compared against 144 rated, priced models on this lens: 48 models dominate it and give up nothing, 4 more dominate it but give something up. Llama 3.1 70B Instruct scores 1260.9 at $0.720 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 |
| --- | --- | --- | --- |
| [MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) | 1492.7 +231.8 | $0.540/M | 25% |
| [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) | 1471.4 +210.5 | $0.148/M | 79% |
| [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) | 1463.0 +202.1 | $0.227/M | 68% |
| [Qwen3.7 Plus](/models/qwen__qwen3.7-plus/) | 1454.1 +193.2 | $0.560/M | 22% |
| [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) | 1449.8 +188.9 | $0.175/M | 76% |
| [Gemma 4 31B](/models/google__gemma-4-31b-it/) | 1442.5 +181.6 | $0.205/M | 72% |
| [Hy3](/models/tencent__hy3/) | 1439.0 +178.1 | $0.231/M | 68% |
| [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) | 1434.2 +173.3 | $0.123/M | 83% |
| [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) | 1431.9 +171.0 | $0.113/M | 84% |
| [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) | 1430.9 +170.0 | $0.450/M | 38% |
| [MiniMax M3](/models/minimax__minimax-m3/) | 1426.5 +165.6 | $0.525/M | 27% |
| [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) | 1424.6 +163.7 | $0.394/M | 45% |
| [Beam 1.0 501B A23B](/models/reflection__beam-1.0-501b-a23b/) | 1424.3 +163.4 | $0.600/M | 17% |
| [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) | 1422.3 +161.4 | $0.305/M | 58% |
| [Qwen3 VL 235B A22B Instruct](/models/qwen__qwen3-vl-235b-a22b-instruct/) | 1420.0 +159.1 | $0.370/M | 49% |
| [DeepSeek V3.1](/models/deepseek__deepseek-chat-v3.1/) | 1419.8 +158.9 | $0.453/M | 37% |
| [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) | 1419.2 +158.3 | $0.205/M | 72% |
| [Qwen3.5-122B-A10B](/models/qwen__qwen3.5-122b-a10b/) | 1417.5 +156.6 | $0.715/M | 1% |
| [DeepSeek V3.1 Terminus](/models/deepseek__deepseek-v3.1-terminus/) | 1417.3 +156.4 | $0.453/M | 37% |
| [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) | 1417.2 +156.3 | $0.343/M | 52% |
| [Gemini 3.1 Flash Lite Preview](/models/google__gemini-3.1-flash-lite-preview/) | 1416.2 +155.3 | $0.563/M | 22% |
| [Inkling Small](/models/thinkingmachines__inkling-small/) | 1414.3 +153.4 | $0.638/M | 11% |
| [Qwen3.5-27B](/models/qwen__qwen3.5-27b/) | 1408.6 +147.7 | $0.536/M | 26% |
| [Inkling 2 Small](/models/thinkingmachines__inkling-2-small/) | 1402.6 +141.7 | $0.475/M | 34% |
| [Claude Haiku 5.5](/models/anthropic__claude-haiku-5.5/) | 1397.5 +136.6 | $0.200/M | 72% |
| [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) | 1397.1 +136.2 | $0.114/M | 84% |
| [Qwen3.5-35B-A3B](/models/qwen__qwen3.5-35b-a3b/) | 1394.8 +133.9 | $0.355/M | 51% |
| [GPT-6 Luna](/models/openai__gpt-6-luna/) | 1390.2 +129.3 | $0.200/M | 72% |
| [Solar Pro 4](/models/upstage__solar-pro4/) | 1388.3 +127.4 | $0.525/M | 27% |
| [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) | 1383.7 +122.8 | $0.143/M | 80% |
| [GLM 4.5 Air](/models/z-ai__glm-4.5-air/) | 1383.7 +122.8 | $0.310/M | 57% |
| [GLM 4.6V](/models/z-ai__glm-4.6v/) | 1376.4 +115.5 | $0.450/M | 38% |
| [DeepSeek V3 0324](/models/deepseek__deepseek-chat-v3-0324/) | 1374.6 +113.7 | $0.438/M | 39% |
| [GPT-5 Mini](/models/openai__gpt-5-mini/) | 1373.5 +112.6 | $0.688/M | 5% |
| [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) | 1371.8 +110.9 | $0.463/M | 36% |
| [gpt-oss-120b](/models/openai__gpt-oss-120b/) | 1365.4 +104.5 | $0.060/M | 92% |
| [MiniMax M2.5](/models/minimax__minimax-m2.5/) | 1359.2 +98.3 | $0.440/M | 39% |
| [Gemma 3 27B](/models/google__gemma-3-27b-it/) | 1357.8 +96.9 | $0.100/M | 86% |
| [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) | 1350.7 +89.8 | $0.145/M Price under confirmation since Nov 21, 2026 | 80% |
| [GPT-4.1 Mini](/models/openai__gpt-4.1-mini/) | 1340.5 +79.6 | $0.700/M | 3% |
| [Qwen3 32B](/models/qwen__qwen3-32b/) | 1340.1 +79.2 | $0.248/M | 66% |
| [Gemma 3 12B](/models/google__gemma-3-12b-it/) | 1334.2 +73.3 | $0.075/M | 90% |
| [DeepSeek V3](/models/deepseek__deepseek-chat/) | 1332.5 +71.6 | $0.500/M | 31% |
| [GPT-5 Nano](/models/openai__gpt-5-nano/) | 1320.0 +59.1 | $0.138/M | 81% |
| [Granite 4.2 8B](/models/ibm-granite__granite-4.2-8b/) | 1318.8 +57.9 | $0.083/M | 89% |
| [gpt-oss-20b](/models/openai__gpt-oss-20b/) | 1287.6 +26.7 | $0.034/M | 95% |
| [GPT-4.1 Nano](/models/openai__gpt-4.1-nano/) | 1284.8 +23.9 | $0.175/M | 76% |
| [Llama 3.3 70B Instruct](/models/meta-llama__llama-3.3-70b-instruct/) | 1274.3 +13.4 | $0.280/M | 61% |

## 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 30B A3B](/models/qwen__qwen3-30b-a3b/) | 1316.8 | $0.215/M | context |
| [Gemma 3 4B](/models/google__gemma-3-4b-it/) | 1290.8 | $0.043/M | tools |
| [GPT-4o-mini (2024-07-18)](/models/openai__gpt-4o-mini-2024-07-18/) | 1286.4 | $0.263/M | context |
| [Qwen2.5 72B Instruct](/models/qwen__qwen-2.5-72b-instruct/) | 1269.1 | $0.370/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/)
