Value ranking
Best value on Frontier Composite
As of October 25, 2026, the best value on Frontier Composite is DeepSeek V4.1 Flash, at 3782.00 normalized points per dollar of input price ($0.02 per million tokens, score 75.6).
Saturation-resistant composite capability score stitched together from ~40 underlying benchmarks using Item Response Theory. Each benchmark is weighted by its fitted difficulty and discriminative slope, so doing well on hard, contamination-resistant evals (FrontierMath, ARC-AGI 2, Humanity's Last Exam) moves the score and saturated benchmarks contribute almost nothing. Imported per-model from Epoch AI's published index; we anchor it to the same min-max scale we use for every other benchmark so it's directly weightable in scenarios.
“Value” is normalized benchmark score (0–100 for this leaderboard cohort) divided by input price per million tokens. Higher means more capability per dollar on this axis only — always sanity-check latency, context length, and your real workload.
- 1DeepSeek V4.1 FlashDeepSeek3782.0075.6 / $0.02/M
- 2gpt-oss-20bOpenAI2289.4441.2 / $0.02/M
- 3Qwen3.7 FlashAlibaba (Qwen)1773.3353.2 / $0.03/M
- 4GPT-5 nanoOpenAI1762.4044.1 / $0.03/M
- 5DeepSeek V4 Flash 0731DeepSeek1740.0573.4 / $0.04/M
- 6GPT-6 LunaOpenAI1543.8077.2 / $0.05/M
- 7Claude Haiku 5.5Anthropic820.4082.0 / $0.10/M
- 8GPT-5.6 LunaOpenAI767.1076.7 / $0.10/M
- 9Gemini 2.5 Flash LiteGoogle677.6033.9 / $0.05/M
- 10DeepSeek V4 Flash 0423DeepSeek627.3657.1 / $0.09/M
- 11GPT-5.4 NanoOpenAI569.4056.9 / $0.10/M
- 12Qwen3 32BAlibaba (Qwen)532.1342.6 / $0.08/M
- 13Qwen3 235BAlibaba (Qwen)488.3344.0 / $0.09/M
- 14GLM 5.3 FlashZhipu AI (GLM)468.3370.3 / $0.15/M
- 15GPT-5 miniOpenAI445.1255.6 / $0.13/M
- 16Gemini 3.1 Flash LiteGoogle428.8053.6 / $0.13/M
- 17Qwen3 30B A3BAlibaba (Qwen)372.5044.7 / $0.12/M
- 18Gemini 2.0 FlashGoogle365.6036.6 / $0.10/M
- 19Gemini 3.5 Flash LiteGoogle365.5354.8 / $0.15/M
- 20Qwen3 14BAlibaba (Qwen)350.5042.1 / $0.12/M
- 21Gemini 2.5 FlashGoogle340.2051.0 / $0.15/M
- 22Gemini 1.5 FlashGoogle338.6725.4 / $0.08/M
- 23Gemma 3 27BGoogle332.6326.6 / $0.08/M
- 24Gemma 4 26B A4BGoogle327.3349.1 / $0.15/M
- 25Qwen3.5-35B-A3BAlibaba (Qwen)309.2350.3 / $0.16/M
AI Model Analyzer does not recommend specific vendors; rankings are derived from public data only.