value rankings
Intelligence Per Dollar
Benchmark points per blended dollar across every credibly ranked model. Scores are min-max normalized across 256 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
| # | Model | Score | % of top score | In / Out per 1M | Blended $/1M | Value |
|---|---|---|---|---|---|---|
| 1 | inclusionAI: Ling 3.0 Flash VL BEST VALUEinclusionai/ling-3.0-flash-vl | 38.6 | 39% | $0.02 / $0.06 | $0.03 | 100.0 |
| 2 | inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flash | 30.4 | 30% | $0.02 / $0.06 | $0.03 | 77.9 |
| 3 | Z.ai: GLM 5.3 Flash (batch)z-ai/glm-5.3-flash:batch | 70.6 | 71% | $0.06 / $0.20 | $0.10 | 60.0 |
| 4 | Anthropic: Claude Haiku 5.5 (batch)anthropic/claude-haiku-5.5:batch | 73.6 | 74% | $0.05 / $0.25 | $0.10 | 59.4 |
| 5 | OpenAI: gpt-oss-120b (batch)openai/gpt-oss-120b:batch | 39.2 | 39% | $0.03 / $0.14 | $0.06 | 56.3 |
| 6 | OpenAI: gpt-oss-20bopenai/gpt-oss-20b | 24.3 | 24% | $0.02 / $0.09 | $0.04 | 54.5 |
| 7 | OpenAI: GPT-6 Luna (batch)openai/gpt-6-luna:batch | 63.8 | 64% | $0.05 / $0.25 | $0.10 | 51.5 |
| 8 | inclusionAI: Ling 3.0 Flash Fininclusionai/ling-3.0-flash-fin | 35.0 | 35% | $0.04 / $0.12 | $0.06 | 45.3 |
| 9 | OpenAI: gpt-oss-20b (batch)openai/gpt-oss-20b:batch | 24.3 | 24% | $0.02 / $0.11 | $0.05 | 42.6 |
| 10 | Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-2501 | 28.8 | 29% | $0.05 / $0.08 | $0.06 | 40.4 |
| 11 | Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct | 59.6 | 60% | $0.09 / $0.25 | $0.13 | 36.2 |
| 12 | Upstage: Solar Mini 4upstage/solar-mini4 | 37.7 | 38% | $0.05 / $0.20 | $0.09 | 34.8 |
| 13 | Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 50.9 | 51% | $0.08 / $0.26 | $0.12 | 33.9 |
| 14 | DeepSeek: DeepSeek V4.1 Flash (batch)deepseek/deepseek-v4.1-flash:batch | 66.3 | 66% | $0.11 / $0.34 | $0.17 | 31.8 |
| 15 | Anthropic: Claude Haiku 5.5anthropic/claude-haiku-5.5 | 73.6 | 74% | $0.10 / $0.50 | $0.20 | 29.7 |
| 16 | Xiaomi: MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash | 63.3 | 63% | $0.14 / $0.28 | $0.18 | 29.2 |
| 17 | Google: Gemma 3 4Bgoogle/gemma-3-4b-it | 21.3 | 21% | $0.05 / $0.10 | $0.06 | 27.5 |
| 18 | Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507 | 66.5 | 66% | $0.09 / $0.55 | $0.21 | 26.2 |
| 19 | Google: Gemma 4 31Bgoogle/gemma-4-31b-it | 49.4 | 49% | $0.09 / $0.34 | $0.15 | 26.1 |
| 20 | OpenAI: GPT-6 Lunaopenai/gpt-6-luna | 63.8 | 64% | $0.10 / $0.50 | $0.20 | 25.7 |
| 21 | Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flash | 70.6 | 71% | $0.03 / $0.90 | $0.24 | 23.3 |
| 22 | Upstage: Solar Pro 4upstage/solar-pro4 | 45.3 | 45% | $0.09 / $0.36 | $0.16 | 23.2 |
| 23 | OpenAI: GPT-5.6 Luna (batch)openai/gpt-5.6-luna:batch | 62.3 | 62% | $0.10 / $0.60 | $0.23 | 22.3 |
| 24 | Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flash | 37.8 | 38% | $0.06 / $0.40 | $0.15 | 21.0 |
| 25 | Qwen: Qwen3 32Bqwen/qwen3-32b | 33.1 | 33% | $0.08 / $0.28 | $0.13 | 20.5 |
| 26 | DeepSeek: DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | 66.3 | 66% | $0.15 / $0.60 | $0.26 | 20.4 |
| 27 | OpenAI: GPT-5 Nano (batch)openai/gpt-5-nano:batch | 17.1 | 17% | $0.03 / $0.20 | $0.07 | 20.1 |
| 28 | Inception: Mercury 2.5inception/mercury-2.5 | 16.0 | 16% | $0.04 / $0.15 | $0.07 | 19.1 |
| 29 | OpenAI: GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batch | 16.7 | 17% | $0.05 / $0.20 | $0.09 | 15.4 |
| 30 | DeepSeek: DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp | 57.7 | 58% | $0.22 / $0.65 | $0.32 | 14.4 |
Budget champions : 80+ score, cheapest first
| # | Model | Score | % of top score | In / Out per 1M | Blended $/1M | Value |
|---|---|---|---|---|---|---|
| 1 | Google: Gemini 2.5 Pro (batch)google/gemini-2.5-pro:batch | 94.2 | 94% | $0.62 / $5.00 | $1.72 | 4.4 |
| 2 | OpenAI: o4 Mini Highopenai/o4-mini-high | 81.0 | 81% | $1.10 / $4.40 | $1.93 | 3.4 |
| 3 | OpenAI: GPT-6.1 Sol (batch)openai/gpt-6.1-sol:batch | 89.2 | 89% | $1.00 / $5.00 | $2.00 | 3.6 |
| 4 | Anthropic: Claude Sonnet 5.5 (batch)anthropic/claude-sonnet-5.5:batch | 97.0 | 97% | $1.00 / $5.00 | $2.00 | 3.9 |
| 5 | OpenAI: GPT-6 Sol (batch)openai/gpt-6-sol:batch | 81.4 | 81% | $1.00 / $5.00 | $2.00 | 3.3 |
| 6 | Meta: Muse Spark 1.3meta/muse-spark-1.3 | 82.3 | 82% | $1.25 / $4.25 | $2.00 | 3.3 |
| 7 | OpenAI: GPT-5.6 Sol (batch)openai/gpt-5.6-sol:batch | 80.2 | 80% | $1.00 / $5.00 | $2.00 | 3.2 |
| 8 | OpenAI: GPT-5.4 (batch)openai/gpt-5.4:batch | 80.9 | 81% | $1.25 / $7.50 | $2.81 | 2.3 |
| 9 | Google: Gemini 2.5 Progoogle/gemini-2.5-pro | 94.2 | 94% | $1.25 / $10.00 | $3.44 | 2.2 |
| 10 | OpenAI: GPT-6.1 Solopenai/gpt-6.1-sol | 89.2 | 89% | $2.00 / $10.00 | $4.00 | 1.8 |
Free models with credible scores
Per-dollar math breaks at $0. These are simply the strongest free options:
- inclusionAI: Ling 3.1 Flash : score 69.3
- Google: Gemma 4 26B A4B (free) : score 50.9
- Google: Gemma 4 31B (free) : score 49.4
- Thinking Machines: Inkling Small (free) : score 40.6
- Thinking Machines: Inkling (free) : score 39.4
- NVIDIA: Nemotron 3 Ultra (free) : score 35.5
- NVIDIA: Nemotron 3 Super (free) : score 16.9
- NVIDIA: Nemotron 3.5 Lightning (free) : score 16.9
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.