value rankings

Intelligence Per Dollar

Benchmark points per blended dollar across every credibly ranked model. Scores are min-max normalized across 47 models with 4+ independent benchmarks; cost assumes a typical 3:1 input:output token mix. Leader = 100.

This is not a quality ranking. #1 here means the most benchmark points per dollar, so a mid-scoring budget model will outrank a frontier model that costs 100x more. Check the Score and % of top score columns for raw capability, and use the task rankings when output quality is what compounds in your workflow.

Value leaderboard

#ModelScore% of top scoreIn / Out per 1MBlended $/1MValue
1OpenAI: gpt-oss-120b BEST VALUEopenai/gpt-oss-120b51.852%$0.04 / $0.18$0.07100.0
2OpenAI: gpt-oss-20bopenai/gpt-oss-20b37.337%$0.03 / $0.14$0.0694.2
3DeepSeek: DeepSeek V4 Flashdeepseek/deepseek-v4-flash80.481%$0.10 / $0.20$0.1294.1
4Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it54.655%$0.06 / $0.33$0.1361.4
5Google: Gemma 4 31Bgoogle/gemma-4-31b-it68.569%$0.12 / $0.35$0.1855.3
6Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flash54.154%$0.06 / $0.40$0.1553.5
7DeepSeek: DeepSeek V3deepseek/deepseek-chat84.184%$0.20 / $0.80$0.3534.4
8Google: Gemma 3 4Bgoogle/gemma-3-4b-it12.713%$0.05 / $0.10$0.0629.1
9Google: Gemma 3 27Bgoogle/gemma-3-27b-it17.017%$0.08 / $0.16$0.1024.4
10DeepSeek: DeepSeek V4 Prodeepseek/deepseek-v4-pro88.188%$0.43 / $0.87$0.5423.2
11Qwen: Qwen3 8Bqwen/qwen3-8b18.218%$0.05 / $0.40$0.1419.0
12MoonshotAI: Kimi K2.5moonshotai/kimi-k2.580.280%$0.35 / $1.89$0.7315.6
13Z.ai: GLM 4.7z-ai/glm-4.773.774%$0.40 / $1.75$0.7414.3
14OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nano16.717%$0.10 / $0.40$0.1813.7
15Z.ai: GLM 5z-ai/glm-585.085%$0.60 / $1.92$0.9313.1
16Qwen: Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b78.379%$0.39 / $2.34$0.8812.8
17Meta: Llama 4 Maverickmeta-llama/llama-4-maverick18.018%$0.15 / $0.60$0.269.8
18MoonshotAI: Kimi K2.6moonshotai/kimi-k2.688.989%$0.67 / $3.39$1.359.4
19Z.ai: GLM 5.1z-ai/glm-5.185.786%$0.98 / $3.08$1.508.2
20OpenAI: GPT-4.1 Miniopenai/gpt-4.1-mini39.239%$0.40 / $1.60$0.708.0
21Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash42.242%$0.30 / $2.50$0.857.1
22xAI: Grok 4.20x-ai/grok-4.2074.775%$1.25 / $2.50$1.566.9
23Z.ai: GLM 4.5z-ai/glm-4.546.647%$0.60 / $2.20$1.006.7
24Anthropic: Claude 3 Haikuanthropic/claude-3-haiku16.917%$0.25 / $1.25$0.504.8
25OpenAI: o4 Miniopenai/o4-mini61.662%$1.10 / $4.40$1.934.6
26OpenAI: GPT-5openai/gpt-582.082%$1.25 / $10.00$3.443.4
27OpenAI: o3 Mini Highopenai/o3-mini-high44.244%$1.10 / $4.40$1.933.3
28OpenAI: o3openai/o374.274%$2.00 / $8.00$3.503.0
29Google: Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview92.493%$2.00 / $12.00$4.502.9
30OpenAI: GPT-5.2openai/gpt-5.289.390%$1.75 / $14.00$4.812.7

Budget champions : 80+ score, cheapest first

#ModelScore% of top scoreIn / Out per 1MBlended $/1MValue
1DeepSeek: DeepSeek V4 Flashdeepseek/deepseek-v4-flash80.481%$0.10 / $0.20$0.1294.1
2DeepSeek: DeepSeek V3deepseek/deepseek-chat84.184%$0.20 / $0.80$0.3534.4
3DeepSeek: DeepSeek V4 Prodeepseek/deepseek-v4-pro88.188%$0.43 / $0.87$0.5423.2
4MoonshotAI: Kimi K2.5moonshotai/kimi-k2.580.280%$0.35 / $1.89$0.7315.6
5Z.ai: GLM 5z-ai/glm-585.085%$0.60 / $1.92$0.9313.1
6MoonshotAI: Kimi K2.6moonshotai/kimi-k2.688.989%$0.67 / $3.39$1.359.4
7Z.ai: GLM 5.1z-ai/glm-5.185.786%$0.98 / $3.08$1.508.2
8OpenAI: GPT-5openai/gpt-582.082%$1.25 / $10.00$3.443.4
9Google: Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview92.493%$2.00 / $12.00$4.502.9
10OpenAI: GPT-5.2openai/gpt-5.289.390%$1.75 / $14.00$4.812.7

Assumptions

Value = blended benchmark score divided by blended price per million tokens, indexed to the leader. A 3:1 input:output ratio fits most chat and RAG workloads; estimate your exact mix with the cost calculator. Scoring details in the methodology. Models with fewer than 4 independent benchmarks are excluded rather than guessed.