---
title: "Compare alternatives to Llama 3.1 70B Instruct · Undominated.ai"
canonical: https://undominated.ai/alternatives/meta-llama__llama-3.1-70b-instruct/
description: "79 alternatives score at least as high as Llama 3.1 70B Instruct and cost no more under at least one listed workload. 72 preserve recorded capabilities; 7 have named trade-offs."
---

# Compare alternatives to Llama 3.1 70B Instruct · Undominated.ai

> 79 alternatives score at least as high as Llama 3.1 70B Instruct and cost no more under at least one listed workload. 72 preserve recorded capabilities; 7 have named trade-offs.

# Alternatives to Llama 3.1 70B Instruct

Meta · LMArena 1260.9 · $0.720/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.

## 72 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, **79** score at least as high as Llama 3.1 70B Instruct and cost no more under at least one listed workload, with at least one of those dimensions improved. **72** match or beat its recorded context, maximum output, input modes, tool use and extended reasoning. **7** 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 | Llama 3.1 70B Instruct $/M | Recorded capabilities preserved | Recorded capability losses |
| --- | --- | --- | --- |
| Balanced | $0.720 | 53 | 5 |
| Summarise | $0.720 | 72 | 7 |
| Chat | $0.720 | 48 | 5 |
| Code gen | $0.720 | 37 | 4 |
| Agentic | $0.720 | 69 | 7 |

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 | 1260.9 |
| --- | --- |
| Context window | 131K |
| Max output | 16K |
| Input modes | text |
| Tool use | yes |
| Extended reasoning | no |

Preserving recorded capabilities requires matching or beating these fields. [Full record for Llama 3.1 70B Instruct](/models/meta-llama__llama-3.1-70b-instruct/), or [check Llama 3.1 70B Instruct against the whole catalogue](/check/meta-llama__llama-3.1-70b-instruct/).

## Recorded capabilities preserved 72

Each option has a higher score or a lower price, with neither dimension worse under the listed workloads. It matches or beats Llama 3.1 70B Instruct on recorded context, maximum output, input modes, tool use and extended reasoning.

| # | Model | Intelligence | $/M | Holds under |
| --- | --- | --- | --- | --- |
| 1 | [MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) Xiaomi | 1491 +230.1 | $0.540 | Balanced −25% Summarise −54% Chat −34% Code gen −8% Agentic −66% |
| 2 | [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) Z.ai | 1469.6 +208.7 | $0.238 | Balanced −67% Summarise −81% Chat −65% Code gen −51% Agentic −82% |
| 3 | [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) DeepSeek | 1462.5 +201.6 | $0.182 | Balanced −75% Summarise −91% Chat −66% Code gen −50% Agentic −85% |
| 4 | [MiMo-V2.5-Pro](/models/xiaomi__mimo-v2.5-pro/) Xiaomi | 1465 +204.1 | $0.544 | Balanced −24% Summarise −54% Chat −33% Code gen −8% Agentic −66% |
| 5 | [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) Xiaomi | 1456.4 +195.5 | $0.175 | Balanced −76% Summarise −85% Chat −78% Code gen −70% Agentic −89% |
| 6 | [Qwen3.7 Plus](/models/qwen__qwen3.7-plus/) Qwen | 1454.6 +193.7 | $0.560 | Balanced −22% Summarise −59% Chat −13% Agentic −57% |
| 7 | [Gemma 4 31B](/models/google__gemma-4-31b-it/) Google | 1443.4 +182.5 | $0.205 | Balanced −72% Summarise −79% Chat −66% Code gen −59% Agentic −75% |
| 8 | [Hy3](/models/tencent__hy3/) Tencent | 1440.7 +179.8 | $0.231 | Balanced −68% Summarise −83% Chat −64% Code gen −50% Agentic −82% |
| 9 | [Qwen3.8 27B](/models/qwen__qwen3.8-27b/) Qwen | 1440.7 +179.8 | $0.562 | Balanced −22% Summarise −75% Agentic −49% |
| 10 | [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) Google | 1433.9 +173 | $0.127 | Balanced −82% Summarise −90% Chat −79% Code gen −72% Agentic −89% |
| 11 | [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) DeepSeek | 1432.1 +171.2 | $0.113 | Balanced −84% Summarise −90% Chat −86% Code gen −81% Agentic −92% |
| 12 | [MiniMax M3](/models/minimax__minimax-m3/) MiniMax | 1432.1 +171.2 | $0.485 | Balanced −33% Summarise −64% Chat −25% Agentic −63% |
| 13 | [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) Xiaomi | 1427.5 +166.6 | $0.175 | Balanced −76% Summarise −85% Chat −78% Code gen −70% Agentic −89% |
| 14 | [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) OpenAI | 1431 +170.1 | $0.450 | Balanced −38% Summarise −72% Chat −24% Agentic −66% |
| 15 | [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) DeepSeek | 1424.5 +163.6 | $0.290 | Balanced −60% Summarise −68% Chat −63% Code gen −55% Agentic −72% |
| 16 | [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) DeepSeek | 1422.4 +161.5 | $0.305 | Balanced −58% Summarise −62% Chat −55% Code gen −51% Agentic −60% |
| 17 | [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) Qwen | 1419.3 +158.4 | $0.205 | Balanced −72% Summarise −84% Chat −62% Code gen −49% Agentic −78% |
| 18 | [Qwen3 VL 235B A22B Instruct](/models/qwen__qwen3-vl-235b-a22b-instruct/) Qwen | 1420.1 +159.2 | $0.370 | Balanced −49% Summarise −71% Chat −38% Code gen −17% Agentic −65% |
| 19 | [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) Qwen | 1417.3 +156.4 | $0.268 | Balanced −63% Summarise −82% Chat −49% Code gen −30% Agentic −72% |
| 20 | [DeepSeek V3.1](/models/deepseek__deepseek-chat-v3.1/) DeepSeek | 1419.7 +158.8 | $0.453 | Balanced −37% Summarise −57% Chat −22% Code gen −2% Agentic −47% |
| 21 | [DeepSeek V3.1 Terminus](/models/deepseek__deepseek-v3.1-terminus/) DeepSeek | 1417.1 +156.2 | $0.453 | Balanced −37% Summarise −57% Chat −22% Code gen −2% Agentic −47% |
| 22 | [Gemini 3.1 Flash Lite Preview](/models/google__gemini-3.1-flash-lite-preview/) Google | 1415.7 +154.8 | $0.563 | Balanced −22% Summarise −66% Chat −5% Agentic −58% |
| 23 | [Qwen3.5-122B-A10B](/models/qwen__qwen3.5-122b-a10b/) Qwen | 1417.1 +156.2 | $0.715 | Balanced −1% Summarise −51% Agentic −26% |
| 24 | [Inkling Small](/models/thinkingmachines__inkling-small/) Thinking Machines | 1413.7 +152.8 | $0.638 | Balanced −11% Summarise −46% Chat −10% Agentic −51% |
| 25 | [Qwen3.5-27B](/models/qwen__qwen3.5-27b/) Qwen | 1408.9 +148 | $0.536 | Balanced −26% Summarise −63% Agentic −44% |
| 26 | [Step 3.5 Flash](/models/stepfun__step-3.5-flash/) StepFun | 1403 +142.1 | $0.150 | Balanced −79% Summarise −85% Chat −75% Code gen −69% Agentic −82% |
| 27 | [MiniMax M2.7](/models/minimax__minimax-m2.7/) MiniMax | 1404.6 +143.7 | $0.525 | Balanced −27% Summarise −62% Chat −18% Agentic −59% |
| 28 | [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) Qwen | 1397 +136.1 | $0.114 | Balanced −84% Summarise −90% Chat −80% Code gen −75% Agentic −87% |
| 29 | [Qwen3.5-35B-A3B](/models/qwen__qwen3.5-35b-a3b/) Qwen | 1394.4 +133.5 | $0.355 | Balanced −51% Summarise −78% Chat −37% Code gen −10% Agentic −70% |
| 30 | [GPT-6 Luna](/models/openai__gpt-6-luna/) OpenAI | 1391.5 +130.6 | $0.200 | Balanced −72% Summarise −87% Chat −68% Code gen −54% Agentic −85% |
| 31 | [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) Qwen | 1384.1 +123.2 | $0.143 | Balanced −80% Summarise −86% Chat −76% Code gen −70% Agentic −83% |
| 32 | [GLM 4.5 Air](/models/z-ai__glm-4.5-air/) Z.ai | 1383.9 +123 | $0.310 | Balanced −57% Summarise −81% Chat −46% Code gen −23% Agentic −76% |
| 33 | [Solar Pro 4](/models/upstage__solar-pro4/) Upstage | 1386.2 +125.3 | $0.525 | Balanced −27% Summarise −62% Chat −18% Agentic −59% |
| 34 | [GLM 4.6V](/models/z-ai__glm-4.6v/) Z.ai | 1376.8 +115.9 | $0.450 | Balanced −38% Summarise −64% Chat −35% Code gen −11% Agentic −66% |
| 35 | [DeepSeek V3 0324](/models/deepseek__deepseek-chat-v3-0324/) DeepSeek | 1375 +114.1 | $0.438 | Balanced −39% Summarise −60% Chat −24% Code gen −3% Agentic −50% |
| 36 | [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) OpenAI | 1372.1 +111.2 | $0.463 | Balanced −36% Summarise −72% Chat −21% Agentic −65% |
| 37 | [gpt-oss-120b](/models/openai__gpt-oss-120b/) OpenAI | 1365.4 +104.5 | $0.065 | Balanced −91% Summarise −95% Chat −88% Code gen −84% Agentic −93% |
| 38 | [GPT-5 Mini](/models/openai__gpt-5-mini/) OpenAI | 1373.2 +112.3 | $0.688 | Balanced −5% Summarise −62% Agentic −47% |
| 39 | [Qwen3 Next 80B A3B Thinking](/models/qwen__qwen3-next-80b-a3b-thinking/) Qwen | 1368.3 +107.4 | $0.413 | Balanced −43% Summarise −72% Chat −21% Agentic −57% |
| 40 | [Gemma 3 27B](/models/google__gemma-3-27b-it/) Google | 1357.8 +96.9 | $0.100 | Balanced −86% Summarise −88% Chat −84% Code gen −82% Agentic −87% |
| 41 | [MiniMax M2.5](/models/minimax__minimax-m2.5/) MiniMax | 1359.3 +98.4 | $0.521 | Balanced −28% Summarise −62% Chat −19% Agentic −60% |
| 42 | [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) Z.ai | 1350.9 +90 | $0.145 | Balanced −80% Summarise −91% Chat −75% Code gen −64% Agentic −89% |
| 43 | [Qwen3 32B](/models/qwen__qwen3-32b/) Qwen | 1340.1 +79.2 | $0.130 | Balanced −82% Summarise −88% Chat −78% Code gen −72% Agentic −85% |
| 44 | [Trinity Large Thinking](/models/arcee-ai__trinity-large-thinking/) Arcee | 1340 +79.1 | $0.388 | Balanced −46% Summarise −69% Chat −43% Code gen −22% Agentic −70% |
| 45 | [Gemma 3 12B](/models/google__gemma-3-12b-it/) Google | 1334.2 +73.3 | $0.075 | Balanced −90% Summarise −92% Chat −88% Code gen −85% Agentic −91% |
| 46 | [MiniMax M2](/models/minimax__minimax-m2/) MiniMax | 1339.9 +79 | $0.525 | Balanced −27% Summarise −63% Chat −20% Agentic −62% |
| 47 | [GPT-4.1 Mini](/models/openai__gpt-4.1-mini/) OpenAI | 1340.4 +79.5 | $0.700 | Balanced −3% Summarise −48% Agentic −44% |
| 48 | [GPT-5 Nano](/models/openai__gpt-5-nano/) OpenAI | 1320 +59.1 | $0.138 | Balanced −81% Summarise −92% Chat −75% Code gen −64% Agentic −89% |
| 49 | [Granite 4.2 8B](/models/ibm-granite__granite-4.2-8b/) IBM | 1317.8 +56.9 | $0.108 | Balanced −85% Summarise −92% Chat −83% Code gen −76% Agentic −91% |
| 50 | [Qwen3 30B A3B](/models/qwen__qwen3-30b-a3b/) Qwen | 1316.6 +55.7 | $0.215 | Balanced −70% Summarise −81% Chat −62% Code gen −52% Agentic −75% |
| 51 | [gpt-oss-20b](/models/openai__gpt-oss-20b/) OpenAI | 1287.7 +26.8 | $0.036 | Balanced −95% Summarise −97% Chat −94% Code gen −92% Agentic −97% |
| 52 | [GPT-4.1 Nano](/models/openai__gpt-4.1-nano/) OpenAI | 1284.8 +23.9 | $0.175 | Balanced −76% Summarise −87% Chat −73% Code gen −62% Agentic −86% |
| 53 | [Llama 3.3 70B Instruct](/models/meta-llama__llama-3.3-70b-instruct/) Meta | 1274.1 +13.2 | $0.201 | Balanced −72% Summarise −79% Chat −67% Code gen −59% Agentic −76% |
| 54 | [Gemini 3.6 Flash](/models/google__gemini-3.6-flash/) Google | 1479.5 +218.6 | $0.708 summarise | Summarise −2% |
| 55 | [GLM 5.3](/models/z-ai__glm-5.3/) Z.ai | 1471.4 +210.5 | $0.346 summarise | Summarise −52% Agentic −10% |
| 56 | [GLM 5.2](/models/z-ai__glm-5.2/) Z.ai | 1470.4 +209.5 | $0.422 summarise | Summarise −41% Agentic −4% |
| 57 | [Kimi K2.6](/models/moonshotai__kimi-k2.6/) Moonshot AI | 1455.5 +194.6 | $0.460 summarise | Summarise −36% Agentic −24% |
| 58 | [DeepSeek V4 Pro 0423](/models/deepseek__deepseek-v4-pro/) DeepSeek | 1445.2 +184.3 | $0.502 summarise | Summarise −30% Agentic −3% |
| 59 | [GLM 5](/models/z-ai__glm-5/) Z.ai | 1446.3 +185.4 | $0.617 summarise | Summarise −14% Agentic −17% |
| 60 | [Kimi K2.5](/models/moonshotai__kimi-k2.5/) Moonshot AI | 1445.2 +184.3 | $0.578 summarise | Summarise −20% Agentic −8% |
| 61 | [GLM 4.6](/models/z-ai__glm-4.6/) Z.ai | 1439.9 +179 | $0.396 summarise | Summarise −45% Agentic −42% |
| 62 | [Qwen3.5 397B A17B](/models/qwen__qwen3.5-397b-a17b/) Qwen | 1438 +177.1 | $0.488 summarise | Summarise −32% Agentic −5% |
| 63 | [Qwen3.6 Plus](/models/qwen__qwen3.6-plus/) Qwen | 1436.7 +175.8 | $0.406 summarise | Summarise −44% Agentic −21% |
| 64 | [GLM 4.7](/models/z-ai__glm-4.7/) Z.ai | 1435.5 +174.6 | $0.376 summarise | Summarise −48% Agentic −43% |
| 65 | [Gemini 3.5 Flash Lite](/models/google__gemini-3.5-flash-lite/) Google | 1434.7 +173.8 | $0.333 summarise | Summarise −54% Agentic −35% |
| 66 | [GLM 4.5](/models/z-ai__glm-4.5/) Z.ai | 1430.3 +169.4 | $0.540 summarise | Summarise −25% Agentic −24% |
| 67 | [R1 0528](/models/deepseek__deepseek-r1-0528/) DeepSeek | 1427.9 +167 | $0.584 summarise | Summarise −19% |
| 68 | [Gemini 2.5 Flash](/models/google__gemini-2.5-flash/) Google | 1417 +156.1 | $0.333 summarise | Summarise −54% Agentic −35% |
| 69 | [Qwen3 235B A22B Thinking 2507](/models/qwen__qwen3-235b-a22b-thinking-2507/) Qwen | 1415.2 +154.3 | $0.334 summarise | Summarise −54% Agentic −25% |
| 70 | [Qwen3 VL 235B A22B Thinking](/models/qwen__qwen3-vl-235b-a22b-thinking/) Qwen | 1400.7 +139.8 | $0.580 summarise | Summarise −19% |
| 71 | [Nova 2 Lite](/models/amazon__nova-2-lite-v1/) Amazon | 1361.8 +100.9 | $0.410 summarise | Summarise −43% Agentic −13% |
| 72 | [MiniMax M1](/models/minimax__minimax-m1/) MiniMax | 1342.8 +81.9 | $0.490 summarise | Summarise −32% Agentic −7% |

## Alternatives with recorded capability losses 7

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 |
| --- | --- | --- | --- | --- |
| [Mercury 2](/models/inception__mercury-2/) Inception | 1355.2 +94.3 | $0.375 | Balanced −48% Summarise −71% Chat −47% Code gen −26% Agentic −73% | 131K → 128K context |
| [DeepSeek V3](/models/deepseek__deepseek-chat/) DeepSeek | 1332.5 +71.6 | $0.500 | Balanced −31% Summarise −54% Chat −13% Agentic −42% | 16K → 16K max output |
| [Gemma 3 4B](/models/google__gemma-3-4b-it/) Google | 1290.8 +29.9 | $0.063 | Balanced −91% Summarise −93% Chat −90% Code gen −89% Agentic −92% | no tool use |
| [GPT-4o-mini (2024-07-18)](/models/openai__gpt-4o-mini-2024-07-18/) OpenAI | 1286.4 +25.5 | $0.263 | Balanced −64% Summarise −79% Chat −57% Code gen −43% Agentic −76% | 131K → 128K context |
| [Qwen2.5 72B Instruct](/models/qwen__qwen-2.5-72b-instruct/) Qwen | 1269 tie | $0.370 | Balanced −49% Summarise −50% Chat −48% Code gen −47% Agentic −49% | 131K → 33K context |
| [Qwen3 235B A22B](/models/qwen__qwen3-235b-a22b/) Qwen | 1366.6 +105.7 | $0.523 summarise | Summarise −27% Agentic −8% | 16K → 8K max output |
| [GLM 4.5V](/models/z-ai__glm-4.5v/) Z.ai | 1332.8 +71.9 | $0.520 summarise | Summarise −28% Agentic −32% | 131K → 66K context |

## 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/)