SmophyAI

Published daily · Next update 02:00 UTC

Themed ranking

Best value

Ranked by quality per dollar - Artificial Analysis Intelligence Index divided by blended price per 1M tokens. A plain ratio, no invented weighting.

As of September 23, 2026, inclusionAI: Ling 3.0 Flash ranks #1 for best value at quality per $ 654.0 pts/$.

  1. #1 inclusionAI: Ling 3.0 Flash - Quality per $ 654.0 pts/$
  2. #2 inclusionAI: Ling 3.0 Flash VL (free) - Quality per $ 273.3 pts/$
  3. #3 inclusionAI: Ling 3.0 Flash Fin (free) - Quality per $ 251.1 pts/$
  4. #4 OpenAI: gpt-oss-20b (batch) - Quality per $ 250.0 pts/$
  5. #5 DeepSeek: DeepSeek V4.1 Flash (batch) - Quality per $ 197.5 pts/$
  6. #6 OpenAI: GPT-6 Luna (batch) - Quality per $ 186.5 pts/$
  7. #7 DeepSeek: DeepSeek V4 Flash 0423 - Quality per $ 180.5 pts/$
  8. #8 Z.ai: GLM 5.3 Flash (batch) - Quality per $ 176.0 pts/$
  9. #9 NVIDIA: Nemotron 3.5 Lightning (free) - Quality per $ 125.9 pts/$
  10. #10 IBM: Granite 4.2 8B - Quality per $ 103.3 pts/$

Top 15 by quality per dollar

This is a ratio, not a capability ranking: an ultra-cheap model with modest absolute quality can outscore a much stronger, pricier one, purely because price sits near zero. Each bar shows its own Quality and Price/1M alongside the ratio. The highlighted bar is today's single best value.

01inclusionAI: Ling 3.0 Flash654.0pts/$Quality 20.6 · $0.03/1M
02inclusionAI: Ling 3.0 Flash VL (free)273.3pts/$Quality 24.6 · $0.09/1M
03inclusionAI: Ling 3.0 Flash Fin (free)251.1pts/$Quality 22.6 · $0.09/1M
04OpenAI: gpt-oss-20b (batch)250.0pts/$Quality 9.0 · $0.04/1M
05DeepSeek: DeepSeek V4.1 Flash (batch)197.5pts/$Quality 39.5 · $0.20/1M
06OpenAI: GPT-6 Luna (batch)186.5pts/$Quality 37.3 · $0.20/1M
07DeepSeek: DeepSeek V4 Flash 0423180.5pts/$Quality 34.3 · $0.19/1M
08Z.ai: GLM 5.3 Flash (batch)176.0pts/$Quality 41.8 · $0.24/1M
09NVIDIA: Nemotron 3.5 Lightning (free)125.9pts/$Quality 12.9 · $0.10/1M
10IBM: Granite 4.2 8B103.3pts/$Quality 11.1 · $0.11/1M
11NVIDIA: Nemotron 3 Nano 30B A3B101.7pts/$Quality 8.9 · $0.09/1M
12Google: Gemma 4 31B (free)101.0pts/$Quality 15.4 · $0.15/1M
13Tencent: Hy3 preview88.8pts/$Quality 25.3 · $0.29/1M
14Xiaomi: MiMo-V2.6-Pro85.1pts/$Quality 46.3 · $0.54/1M
15OpenAI: GPT-5.6 Luna (batch)82.9pts/$Quality 37.3 · $0.45/1M
94 eligible models, sorted by quality per $
#ModelQualityPrice/1MQuality per $
01inclusionAI: Ling 3.0 Flash20.6$0.03654.0 pts/$
02inclusionAI: Ling 3.0 Flash VL (free)24.6$0.09273.3 pts/$
03inclusionAI: Ling 3.0 Flash Fin (free)22.6$0.09251.1 pts/$
04OpenAI: gpt-oss-20b (batch)9.0$0.04250.0 pts/$
05DeepSeek: DeepSeek V4.1 Flash (batch)39.5$0.20197.5 pts/$
06OpenAI: GPT-6 Luna (batch)37.3$0.20186.5 pts/$
07DeepSeek: DeepSeek V4 Flash 042334.3$0.19180.5 pts/$
08Z.ai: GLM 5.3 Flash (batch)41.8$0.24176.0 pts/$
09NVIDIA: Nemotron 3.5 Lightning (free)12.9$0.10125.9 pts/$
10IBM: Granite 4.2 8B11.1$0.11103.3 pts/$
11NVIDIA: Nemotron 3 Nano 30B A3B8.9$0.09101.7 pts/$
12Google: Gemma 4 31B (free)15.4$0.15101.0 pts/$
13Tencent: Hy3 preview25.3$0.2988.8 pts/$
14Xiaomi: MiMo-V2.6-Pro46.3$0.5485.1 pts/$
15OpenAI: GPT-5.6 Luna (batch)37.3$0.4582.9 pts/$
16inclusionAI: Ring-2.6-1T16.6$0.2178.1 pts/$
17NVIDIA: Nemotron 3 Super (free)12.8$0.1774.2 pts/$
18MiniMax: MiniMax M329.2$0.5255.6 pts/$
19OpenAI: GPT-4.1 Nano (batch)9.6$0.1754.9 pts/$
20Google: Gemma 3 12B3.8$0.0750.7 pts/$
21Qwen: Qwen3.6 35B A3B18.2$0.3650.2 pts/$
22Mistral: Ministral 3 3B 25124.8$0.1048.0 pts/$
23Xiaomi: MiMo-V2.5-Pro26.0$0.5447.8 pts/$
24Qwen: Qwen3.7 Plus25.2$0.5645.0 pts/$
25OpenAI: GPT-5.4 Nano (batch)20.7$0.4644.8 pts/$
26OpenAI: gpt-oss-120b11.6$0.2644.2 pts/$
27MiniMax: MiniMax M2.722.8$0.5243.4 pts/$
28Mistral: Mistral Small 4 (batch)11.3$0.2643.0 pts/$
29Mistral: Ministral 3 8B 2512 (batch)5.5$0.1536.7 pts/$
30Meituan: LongCat 2.019.1$0.5236.4 pts/$
31Z.ai: GLM 5.3 (batch)44.8$1.2934.7 pts/$
32Z.ai: GLM 5.2 (free)33.7$1.0033.8 pts/$
33DeepSeek: DeepSeek V3.1 Terminus14.8$0.4532.7 pts/$
34Qwen: Qwen3 Coder Next9.2$0.2931.7 pts/$
35Qwen: Qwen3.8 27B (free)33.7$1.0631.6 pts/$
36Inception: Mercury 211.5$0.3830.7 pts/$
37Mistral: Ministral 3 14B 25126.0$0.2030.0 pts/$
38Upstage: Solar Pro 37.8$0.2629.7 pts/$
39Google: Gemma 3 27B4.9$0.1728.4 pts/$
40Arcee AI: Trinity Large Thinking10.8$0.3927.9 pts/$
41Google: Gemini 3.1 Flash Lite Preview15.6$0.5627.7 pts/$
42Google: Gemini 3.8 Flash (batch)40.9$1.5027.3 pts/$
43Google: Gemini 3.5 Flash Lite (batch)22.2$0.8526.1 pts/$
44Google: Gemini 3.7 Flash (batch)39.1$1.5026.1 pts/$
45OpenAI: GPT-5 Mini (batch)16.8$0.6924.4 pts/$
46Qwen: Qwen3.6 27B21.4$0.9223.4 pts/$
47Google: Gemini 3.6 Flash (batch)34.0$1.5022.7 pts/$
48DeepSeek: DeepSeek V3 03249.7$0.4422.2 pts/$
49Qwen: Qwen3.5-122B-A10B15.6$0.7121.8 pts/$
50NVIDIA: Nemotron 3 Ultra (free)22.9$1.0521.8 pts/$
51Amazon: Nova 2 Lite18.4$0.8521.6 pts/$
52OpenAI: GPT-4.1 Mini (batch)14.8$0.7021.1 pts/$
53Meta: Muse Spark 1.239.6$2.0019.8 pts/$
54SpaceXAI: Grok 4.746.4$2.4019.3 pts/$
55MoonshotAI: Kimi K2.7 Code25.8$1.3519.0 pts/$
56DeepSeek: DeepSeek V4 Pro 042336.0$1.9818.2 pts/$
57Qwen: Qwen3.8 Max53.4$3.0017.8 pts/$
58Z.ai: GLM 5.126.1$1.4817.6 pts/$
59Qwen: Qwen3 235B A22B Thinking 250712.7$0.7517.0 pts/$
60Meta: Muse Spark 1.133.7$2.0016.8 pts/$
61MoonshotAI: Kimi K2 Thinking17.2$1.0816.0 pts/$
62SpaceXAI: Grok 4.3 (batch)24.9$1.5615.9 pts/$
63MoonshotAI: Kimi K2.627.0$1.7115.8 pts/$
64SpaceXAI: Grok 4.644.3$3.0014.8 pts/$
65Qwen: Qwen3.5 397B A17B18.4$1.2914.3 pts/$
66OpenAI: GPT-5.4 Mini (batch)24.1$1.6914.3 pts/$
67Thinking Machines: Inkling (free)25.0$1.7614.2 pts/$
68Qwen: Qwen3.7 Max29.5$2.2113.3 pts/$
69Qwen: Qwen3.8 2.4T A95B39.9$3.0013.3 pts/$
70Qwen: Qwen3 30B A3B Thinking 25079.8$0.7513.1 pts/$
71SpaceXAI: Grok 4.538.8$3.0012.9 pts/$
72Mistral: Mistral Large 3 2512 (batch)9.3$0.7512.4 pts/$
73OpenAI: GPT-6 Sol (batch)47.5$4.0011.9 pts/$
74OpenAI: GPT-5.6 Sol (batch)47.0$4.0011.7 pts/$
75Mistral: Mistral Medium 3.1 (batch)9.2$0.8011.5 pts/$
76Mistral: Devstral 2 25128.6$0.8010.8 pts/$
77DeepSeek: R111.4$1.159.9 pts/$
78Google: Gemini 3.5 Flash (batch)32.6$3.389.7 pts/$
79Anthropic: Claude Sonnet 5 (batch)38.2$4.009.5 pts/$
80OpenAI: GPT-5.6 Terra (batch)42.1$4.509.4 pts/$
81Anthropic: Claude Haiku 4.5 (batch)16.9$2.008.4 pts/$
82MoonshotAI: Kimi K3 (batch)43.6$6.007.3 pts/$
83Anthropic: Claude Opus 5.5 (batch)57.6$8.007.2 pts/$
84Google: Gemini 3.1 Pro Preview (batch)29.7$4.506.6 pts/$
85OpenAI: o3 Mini High11.0$1.935.7 pts/$
86Anthropic: Claude Opus 5 (batch)50.8$10.005.1 pts/$
87Anthropic: Claude Sonnet 4.6 (batch)30.1$6.005.0 pts/$
88Google: Gemini 2.5 Pro (batch)16.1$3.444.7 pts/$
89Anthropic: Claude Opus 4.8 (batch)41.8$10.004.2 pts/$
90Anthropic: Claude Sonnet 4.5 (batch)20.7$6.003.4 pts/$
91OpenAI: GPT-5.5 (batch)38.4$11.253.4 pts/$
92Anthropic: Claude Fable 5.1 (batch)53.4$20.002.7 pts/$
93OpenAI: GPT-6 Astra (batch)52.7$20.002.6 pts/$
94Anthropic: Claude Fable 5 (batch)49.6$20.002.5 pts/$

How this is calculated

Quality per $ = Intelligence Index ÷ blended price per 1M tokens - a plain ratio, not a capability ranking. An ultra-cheap model with modest absolute Quality can outrank a much stronger, pricier one purely because price sits near zero; the Quality and Price/1M columns above show the two real numbers behind every ratio.

What it can't tell you: consistency run-to-run, how costly a wrong answer is for your use case, or whether a task needs multiple attempts. For high-stakes work, weigh the absolute Quality score more than the ratio, and check measured endpoint uptime for consistency.

Source: OpenRouter (openrouter.ai/rankings), as of September 23, 2026.

Benchmark scores: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).

Methodology: www.smophy.ai/benchmark/methodology

Token counts originate from each provider's own tokenizer and are not directly comparable across providers.