# Best Value LLM for Coding in 2026 — Cost-Adjusted Rankings

> Top AI models ranked by coding benchmark performance per dollar. Find the most cost-effective LLM for coding tasks including SWE-bench, LiveCodeBench, and more.

Raw benchmark scores only tell half the story. This ranking divides each model's weighted coding score by its output token price, surfacing models that deliver the most coding capability per dollar spent. A model scoring 70 at $1/1M tokens outranks one scoring 80 at $15/1M tokens here — because for the same budget you get far more coding work done. Use this alongside the standard coding leaderboard to find the sweet spot between performance and cost for your coding workflows.

Canonical page: https://benchlm.ai/best/best-value-coding

Last updated: September 15, 2026

## Rankings

| Rank | Model | Creator | Type | Context | Score |
|------|-------|---------|------|---------|-------|
| 1 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | Proprietary | 1M | 83.9 |
| 2 | [Claude Fable 5](/models/claude-fable) | Anthropic | Proprietary | 1M+ | 77 |
| 3 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | Proprietary | null | 75.7 |
| 4 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | Proprietary | 1.05M | 74.5 |
| 5 | [GPT-5.6 Sol](/models/gpt-5-6-sol) | OpenAI | Proprietary | 1.05M | 74.4 |
| 6 | [Kimi K3](/models/kimi-k3) | Moonshot AI | Pending | 1.05M | 67.8 |
| 7 | [GPT-5.5](/models/gpt-5-5) | OpenAI | Proprietary | 1M | 67.6 |
| 8 | [GPT-5.6 Terra](/models/gpt-5-6-terra) | OpenAI | Proprietary | 1.05M | 67 |
| 9 | [GPT-5.6 Luna](/models/gpt-5-6-luna) | OpenAI | Proprietary | 1.05M | 66.8 |
| 10 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | Google | Proprietary | 1M | 66.5 |
| 11 | [Claude Opus 4.8](/models/claude-opus-4-8) | Anthropic | Proprietary | 1M | 66.4 |
| 12 | [Grok 4.6](/models/grok-4-6) | xAI | Proprietary | 500K | 66.2 |
| 13 | [Claude Sonnet 5](/models/claude-sonnet-5) | Anthropic | Proprietary | 1M | 64 |
| 14 | [Claude Opus 4.7](/models/claude-opus-4-7) | Anthropic | Proprietary | 1M | 62.8 |
| 15 | [Gemini 3.7 Flash](/models/gemini-3-7-flash) | Google | Proprietary | 1M | 62.7 |
| 16 | [Grok 4.5](/models/grok-4-5) | xAI | Proprietary | 500K | 62.1 |
| 17 | [GPT-5.3 Codex](/models/gpt-5-3-codex) | OpenAI | Proprietary | 400K | 62 |
| 18 | [GLM-5.3](/models/glm-5-3) | Z.AI | Open Weight | 1M | 61.4 |
| 19 | [GLM-5.2](/models/glm-5-2) | Z.AI | Open Weight | 1M | 60.9 |
| 20 | [Qwen3.8 Max](/models/qwen3-8-max) | Alibaba | Open Weight | 1M | 60.8 |
| 21 | [Muse Spark 1.2](/models/muse-spark-1-2) | Meta | Proprietary | 1M | 60.1 |
| 22 | [Gemini 3 Pro](/models/gemini-3-pro) | Google | Proprietary | 2M | 59.9 |
| 23 | [Muse Spark 1.1](/models/muse-spark-1-1) | Meta | Proprietary | 1M | 59.7 |
| 24 | [Hy4 preview](/models/hy4-preview) | Tencent | Open Weight | 1M | 59.2 |
| 25 | [Muse Spark](/models/muse-spark) | Meta | Proprietary | 262K | 58.9 |
| 26 | [Ornith-1.5-397B](/models/ornith-1-5-397b) | Ornith AI | Open Weight | 262K | 58.7 |
| 27 | [Gemini 3.6 Flash](/models/gemini-3-6-flash) | Google | Proprietary | 1M | 58.5 |
| 28 | [Hy3](/models/hy3) | Tencent | Open Weight | 256K | 58.1 |
| 29 | [GLM-5.3-Flash](/models/glm-5-3-flash) | Z.AI | Open Weight | 1M | 58.1 |
| 30 | [Qwen3.8-Flash-Next](/models/qwen3-8-flash-next) | Alibaba | Open Weight | 262K | 58 |
| 31 | [Claude Opus 4.7 (Adaptive)](/models/claude-opus-4-7-adaptive) | Anthropic | Proprietary | 1M | 57.7 |
| 32 | [Qwen 3.6 Max (preview)](/models/qwen3-6-max-preview) | Alibaba | Proprietary | 256K | 57.6 |
| 33 | [Gemini 3.5 Flash](/models/gemini-3-5-flash) | Google | Proprietary | 1M | 57.4 |
| 34 | [dots3-note Preview](/models/dots3-note-preview) | Dots Studio | Open Weight | 512K | 57.2 |
| 35 | [Claude Opus 4.6 (Adaptive)](/models/claude-opus-4-6-thinking) | Anthropic | Proprietary | 1M | 56.8 |
| 36 | [Claude Opus 4.5](/models/claude-opus-4-5) | Anthropic | Proprietary | 200K | 56.7 |
| 37 | [Claude Opus 4.6](/models/claude-opus-4-6) | Anthropic | Proprietary | 1M | 56.5 |
| 38 | [GLM-5.1](/models/glm-5-1) | Z.AI | Open Weight | 203K | 56.3 |
| 39 | [GLM-5](/models/glm-5) | Z.AI | Open Weight | 200K | 56.1 |
| 40 | [MiMo-V2.5-Pro](/models/mimo-v2-5-pro) | Xiaomi | Proprietary | 1M | 55.4 |
| 41 | [MiMo-V2-Pro](/models/mimo-v2-pro) | Xiaomi | Proprietary | 1M | 55.3 |
| 42 | [GPT-5.4](/models/gpt-5-4) | OpenAI | Proprietary | 1.05M | 53.9 |
| 43 | [Qwen3.8-27B](/models/qwen3-8-27b) | Alibaba | Open Weight | 262K | 53.9 |
| 44 | [SWE-1.7](/models/swe-1-7) | Cognition | Proprietary | 256K | 53.2 |
| 45 | [GLM-5V-Turbo](/models/glm-5v-turbo) | Z.AI | Proprietary | 200K | 52.8 |
| 46 | [Qwen3.7 Plus](/models/qwen3-7-plus) | Alibaba | Proprietary | 1M | 52.7 |
| 47 | [Apodex 1.1](/models/apodex-1-1) | Apodex | Proprietary | N/A | 52.5 |
| 48 | [Claude Sonnet 4.6](/models/claude-sonnet-4-6) | Anthropic | Proprietary | 200K | 52.3 |
| 49 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | DeepSeek | Proprietary | 1M | 52.3 |
| 50 | [Atria Dawn Preview](/models/atria-dawn-preview) | Shanghai Artificial Intelligence Laboratory | Open Weight | 256K | 51.6 |
| 51 | [GPT-5.2-Codex](/models/gpt-5-2-codex) | OpenAI | Proprietary | 400K | 51.6 |
| 52 | [Kimi K2.7 Code](/models/kimi-k2-7-code) | Moonshot AI | Open Weight | 256K | 50.9 |
| 53 | [Kimi K2.5 (Reasoning)](/models/kimi-k2-5-reasoning) | Moonshot AI | Proprietary | 128K | 50.8 |
| 54 | [Kimi K2.6](/models/kimi-2-6) | Moonshot AI | Open Weight | 256K | 50.8 |
| 55 | [Claude Sonnet 4.5](/models/claude-sonnet-4-5) | Anthropic | Proprietary | 200K | 50.7 |
| 56 | [Kimi K2.5](/models/kimi-k2-5) | Moonshot AI | Open Weight | 256K | 50.6 |
| 57 | [Composer 2.5](/models/composer-2-5) | Cursor | Proprietary | 200K | 50.5 |
| 58 | [MAI-Thinking-1](/models/mai-thinking-1) | Microsoft | Proprietary | 256K | 50.5 |
| 59 | [Ornith-1.0-397B](/models/ornith-1-0-397b) | DeepReinforce AI | Open Weight | 256K | 50.5 |
| 60 | [Qwen3.5 397B](/models/qwen3-5-397b) | Alibaba | Open Weight | 128K | 50.4 |
| 61 | [Qwen3.5-27B](/models/qwen3-5-27b) | Alibaba | Open Weight | 262K | 50 |
| 62 | [BTL-4](/models/btl-4) | Bad Theory Labs | Open Weight | 262K | 50 |
| 63 | [DeepSeek V3.2](/models/deepseek-v3-2) | DeepSeek | Open Weight | 128K | 50 |
| 64 | [MiMo-V2-Flash](/models/mimo-v2-flash) | Xiaomi | Open Weight | 256K | 49.5 |
| 65 | [Qwen3.7 Max](/models/qwen3-7-max) | Alibaba | Proprietary | 1M | 49.4 |
| 66 | [Composer 2](/models/composer-2) | Cursor | Proprietary | 200K | 49 |
| 67 | [MiniMax M3](/models/minimax-m3) | MiniMax | Open Weight | 1M | 48.7 |
| 68 | [MiniMax M2.7](/models/minimax-m2-7) | MiniMax | Open Weight | 200K | 48.6 |
| 69 | [MiniMax M2.5](/models/minimax-m2-5) | MiniMax | Proprietary | 128K | 48.5 |
| 70 | [Muse Glimmer 30B](/models/muse-glimmer-30b) | Meta | Open Weight | 131K | 48.3 |
| 71 | [GPT-5 (medium)](/models/gpt-5-medium) | OpenAI | Proprietary | 128K | 48.3 |
| 72 | [DeepSeek V3.2 (Thinking)](/models/deepseek-v3-2-thinking) | DeepSeek | Open Weight | 128K | 47.8 |
| 73 | [GLM-4.7](/models/glm-4-7) | Z.AI | Open Weight | 200K | 47.7 |
| 74 | [Step 3.7 Flash](/models/step-3-7-flash) | StepFun | Open Weight | 256K | 47.3 |
| 75 | [Mercury 2.5](/models/mercury-2-5) | Inception | Proprietary | 260K | 47.2 |
| 76 | [GLM-4.6](/models/glm-4-6) | Z.AI | Open Weight | 200K | 47.1 |
| 77 | [Qwen3.6 Plus](/models/qwen3-6-plus) | Alibaba | Proprietary | 1M | 46.9 |
| 78 | [ZAYA1-74B-Preview](/models/zaya1-74b-preview) | Zyphra | Open Weight | 256K | 46.8 |
| 79 | [Qwen3.5 Flash](/models/qwen3-5-flash) | Alibaba | Proprietary | 1M | 46.8 |
| 80 | [Ornith-1.5-35B-A3B](/models/ornith-1-5-35b-a3b) | Ornith AI | Open Weight | 262K | 46.8 |
| 81 | [Ornith-1.0-35B](/models/ornith-1-0-35b) | DeepReinforce AI | Open Weight | 256K | 46.7 |
| 82 | [GPT-5.2](/models/gpt-5-2) | OpenAI | Proprietary | 400K | 46.4 |
| 83 | [Ornith-1.5-9B](/models/ornith-1-5-9b) | Ornith AI | Open Weight | 262K | 46.4 |
| 84 | [Gemini 3.1 Pro](/models/gemini-3-1-pro) | Google | Proprietary | 1M | 46.2 |
| 85 | [Ornith-1.0-9B](/models/ornith-1-0-9b) | DeepReinforce AI | Open Weight | 256K | 46.1 |
| 86 | [Grok 4.1 Fast (Reasoning)](/models/grok-4-1-fast-reasoning) | xAI | Proprietary | 2M | 46.1 |
| 87 | [Laguna S 2.1](/models/laguna-s-2-1) | Poolside | Open Weight | 1M | 46 |
| 88 | [Qwen3.5-35B-A3B](/models/qwen3-5-35b-a3b) | Alibaba | Open Weight | 262K | 45.6 |
| 89 | [o3-mini](/models/o3-mini) | OpenAI | Proprietary | 200K | 45.3 |
| 90 | [Qwen3.6-35B-A3B](/models/qwen3-6-35b-a3b) | Alibaba | Open Weight | 262K | 45 |
| 91 | [GPT-5.1](/models/gpt-5-1) | OpenAI | Proprietary | 200K | 45 |
| 92 | [GPT-5.1-Codex](/models/gpt-5-1-codex) | OpenAI | Proprietary | 400K | 44.9 |
| 93 | [K-Exaone](/models/k-exaone) | LG AI Research | Proprietary | 256K | 44.5 |
| 94 | [Hy3 Preview](/models/hy3-preview) | Tencent | Open Weight | 256K | 44.4 |
| 95 | [o1](/models/o1) | OpenAI | Proprietary | 200K | 44.4 |
| 96 | [Gemma 4 12B](/models/gemma-4-12b) | Google | Open Weight | 256K | 44.2 |
| 97 | [o1-preview](/models/o1-preview) | OpenAI | Proprietary | 200K | 44.1 |
| 98 | [Inkling-Small](/models/inkling-small) | Thinking Machines Lab | Open Weight | 1M | 43.8 |
| 99 | [GPT-OSS 120B](/models/gpt-oss-120b) | OpenAI | Open Weight | 128K | 43.7 |
| 100 | [Command A+](/models/command-a-plus) | Cohere | Open Weight | 128K | 43.6 |
| 101 | [MiMo-V2.5](/models/mimo-v2-5) | Xiaomi | Proprietary | 1M | 43.5 |
| 102 | [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) | Google | Proprietary | 1M | 43.3 |
| 103 | [Claude 4.1 Opus](/models/claude-4-1-opus) | Anthropic | Proprietary | 200K | 42.9 |
| 104 | [GPT-5.4 mini](/models/gpt-5-4-mini) | OpenAI | Proprietary | 400K | 42.8 |
| 105 | [Qwen3.5-122B-A10B](/models/qwen3-5-122b-a10b) | Alibaba | Open Weight | 262K | 42.6 |
| 106 | [Gemma 4 31B](/models/gemma-4-31b) | Google | Open Weight | 256K | 42.4 |
| 107 | [Qwen3.6-27B](/models/qwen3-6-27b) | Alibaba | Open Weight | 262K | 41.8 |
| 108 | [Gemini 3 Flash](/models/gemini-3-flash) | Google | Proprietary | 1M | 41.4 |
| 109 | [GPT-4.1](/models/gpt-4-1) | OpenAI | Proprietary | 1M | 41.3 |
| 110 | [Gemma 4 26B A4B](/models/gemma-4-26b-a4b) | Google | Open Weight | 256K | 41.3 |
| 111 | [Grok 4 Fast (Reasoning)](/models/grok-4-fast-reasoning) | xAI | Proprietary | 2M | 41.2 |
| 112 | [Inkling](/models/inkling) | Thinking Machines Lab | Open Weight | 1M | 41.1 |
| 113 | [Mistral Small 4](/models/mistral-small-4) | Mistral | Open Weight | 256K | 41 |
| 114 | [Ling 3.0 Flash](/models/ling-3-0-flash) | InclusionAI | Open Weight | 262K | 40.6 |
| 115 | [Ling 2.6 Flash](/models/ling-2-6-flash) | InclusionAI | Open Weight | 262K | 40.5 |
| 116 | [Nemotron 3 Nano Omni 30B A3B](/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | Open Weight | 256K | 40.4 |
| 117 | [GPT-5 mini](/models/gpt-5-mini) | OpenAI | Proprietary | 128K | 40.3 |
| 118 | [Claude 4 Sonnet](/models/claude-4-sonnet) | Anthropic | Proprietary | 200K | 40.1 |
| 119 | [DeepSeek V3](/models/deepseek-v3) | DeepSeek | Open Weight | 128K | 39.5 |
| 120 | [Gemma 4 E4B](/models/gemma-4-e4b) | Google | Open Weight | 128K | 39.4 |
| 121 | [Mistral Medium 3.5 128B](/models/mistral-medium-3-5-128b) | Mistral | Open Weight | 256K | 39.2 |
| 122 | [Grok Build 0.1](/models/grok-build-0-1) | xAI | Proprietary | 256K | 39.1 |
| 123 | [LFM2.5-2.6B](/models/lfm2-5-2-6b) | LiquidAI | Open Weight | 128K | 39 |
| 124 | [Gemma 4 E2B](/models/gemma-4-e2b) | Google | Open Weight | 128K | 38.8 |
| 125 | [GPT-OSS 20B](/models/gpt-oss-20b) | OpenAI | Open Weight | 128K | 38.7 |
| 126 | [Gemini 3.1 Flash-Lite](/models/gemini-3-1-flash-lite) | Google | Proprietary | 1M | 38.2 |
| 127 | [GPT-5.4 nano](/models/gpt-5-4-nano) | OpenAI | Proprietary | 400K | 37.2 |
| 128 | [Granite 4.2 8B](/models/granite-4-2-8b) | IBM | Open Weight | 128K | 37.2 |
| 129 | [GPT-4.1 mini](/models/gpt-4-1-mini) | OpenAI | Proprietary | 1M | 35.6 |
| 130 | [Gemini 1.5 Pro](/models/gemini-1-5-pro) | Google | Proprietary | 2M | 34.2 |
| 131 | [Claude 3 Opus](/models/claude-3-opus) | Anthropic | Proprietary | 200K | 34 |
| 132 | [Grok 4.3](/models/grok-4-3) | xAI | Proprietary | 1M | 33.7 |
| 133 | [Gemma 3 27B](/models/gemma-3-27b) | Google | Open Weight | 32K | 33.1 |
| 134 | [Gemini 2.5 Pro](/models/gemini-2-5-pro) | Google | Proprietary | 1M | 31.8 |
| 135 | [GPT-4o mini](/models/gpt-4o-mini) | OpenAI | Proprietary | 128K | 31.7 |
| 136 | [Llama 4 Scout](/models/llama-4-scout) | Meta | Open Weight | 10M | 31.1 |
| 137 | [GPT-4.1 nano](/models/gpt-4-1-nano) | OpenAI | Proprietary | 1M | 31.1 |
| 138 | [Nemotron 3.5 Lightning 30B A3B NVFP4](/models/nemotron-3-5-lightning-30b-a3b-nvfp4) | NVIDIA | Open Weight | 1M | 30.3 |
| 139 | [Ministral 3 14B](/models/ministral-3-14b) | Mistral | Open Weight | 128K | 30.2 |
| 140 | [Grok Code Fast 1](/models/grok-code-fast-1) | xAI | Proprietary | 256K | 30 |
| 141 | [Laguna M.1](/models/laguna-m-1) | Poolside | Proprietary | 256K | 29.7 |
| 142 | [Grok 4.20](/models/grok-4-20-beta) | xAI | Proprietary | 2M | 28.4 |
| 143 | [GPT-4 Turbo](/models/gpt-4-turbo) | OpenAI | Proprietary | 128K | 27.8 |
| 144 | [Claude Haiku 4.5](/models/claude-haiku-4-5) | Anthropic | Proprietary | 200K | 27.4 |
| 145 | [Trinity-Large-Thinking](/models/trinity-large-thinking) | Arcee AI | Open Weight | 512K | 27.4 |
| 146 | [Nemotron 3 Ultra](/models/nemotron-3-ultra) | NVIDIA | Open Weight | 1M | 26.6 |
| 147 | [Llama 4 Maverick](/models/llama-4-maverick) | Meta | Open Weight | 1M | 25.7 |
| 148 | [Mistral Large 3](/models/mistral-large-3) | Mistral | Proprietary | 128K | 25.4 |
| 149 | [Laguna XS.2](/models/laguna-xs-2) | Poolside | Open Weight | 256K | 24.7 |
| 150 | [Mercury 2](/models/mercury-2) | Inception | Proprietary | 128K | 24.6 |
| 151 | [Ministral 3 8B](/models/ministral-3-8b) | Mistral | Open Weight | 128K | 21.1 |
| 152 | [Ministral 3 3B](/models/ministral-3-3b) | Mistral | Open Weight | 128K | 19 |

## Key Takeaways

- Top model: [Claude Fable 5.1](/models/claude-fable-5-1) with a score of 83.9
- Best open-weight option: [GLM-5.3](/models/glm-5-3) at #18
- Models included: 152

## Compare the Leaders

- [Claude Fable 5.1 vs Claude Fable 5](/compare/claude-fable-vs-claude-fable-5-1)