Value ranking
Best value on MMMU
As of October 25, 2026, the best value on MMMU is Gemini 2.0 Flash, at 625.70 normalized points per dollar of input price ($0.10 per million tokens, score 62.6).
Massive Multi-discipline Multimodal Understanding; college-exam level questions with images across 30+ subjects.
“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.
- 1Gemini 2.0 FlashGoogle625.7062.6 / $0.10/M
- 2Gemma 3 12BGoogle590.2029.5 / $0.05/M
- 3Gemini 2.5 FlashGoogle562.8784.4 / $0.15/M
- 4Llama 4 ScoutMeta562.8056.3 / $0.10/M
- 5Gemma 3 27BGoogle549.8844.0 / $0.08/M
- 6Llama 4 MaverickMeta358.4567.2 / $0.19/M
- 7Seed 1.6ByteDance Seed284.1671.0 / $0.25/M
- 8Gemini 1.5 FlashGoogle266.0019.9 / $0.08/M
- 9GPT-4o miniOpenAI193.0729.0 / $0.15/M
- 10GPT-5.1OpenAI160.00100.0 / $0.63/M
- 11Gemini 2.5 ProGoogle134.6484.2 / $0.63/M
- 12o4-miniOpenAI81.4789.6 / $1.10/M
- 13o3-miniOpenAI72.5379.8 / $1.10/M
- 14GPT-5OpenAI55.9670.0 / $1.25/M
- 15Qwen2.5 VL 72B InstructAlibaba (Qwen)53.6242.9 / $0.80/M
- 16o3OpenAI46.5993.2 / $2.00/M
- 17Gemini 1.5 ProGoogle37.3846.7 / $1.25/M
- 18Grok 3xAI26.5979.8 / $3.00/M
- 19Claude Sonnet 4.5Anthropic26.4179.2 / $3.00/M
- 20Claude 3.7 SonnetAnthropic23.8671.6 / $3.00/M
- 21Grok 2xAI23.6447.3 / $2.00/M
- 22Claude Sonnet 4Anthropic23.3270.0 / $3.00/M
- 23GPT-4oOpenAI22.1855.5 / $2.50/M
- 24Nova Premier 1.0Amazon20.9852.5 / $2.50/M
- 25o1-miniOpenAI20.2260.7 / $3.00/M
AI Model Analyzer does not recommend specific vendors; rankings are derived from public data only.