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 August 9, 2026, Ling-3.0-flash ranks #1 for best value at quality per $ 1200.0 pts/$.

  1. #1 Ling-3.0-flash - Quality per $ 1200.0 pts/$
  2. #2 inclusionAI: Ling-2.6-flash - Quality per $ 946.7 pts/$
  3. #3 Z.ai: GLM 5.2 (batch) - Quality per $ 489.3 pts/$
  4. #4 DeepSeek: DeepSeek V4 Flash 0423 - Quality per $ 460.4 pts/$
  5. #5 Tencent: Hy3 preview - Quality per $ 423.1 pts/$
  6. #6 OpenAI: gpt-oss-120b - Quality per $ 343.1 pts/$
  7. #7 OpenAI: gpt-oss-20b (free) - Quality per $ 276.4 pts/$
  8. #8 OpenAI: GPT-5.6 Luna (batch) - Quality per $ 232.4 pts/$
  9. #9 Xiaomi: MiMo-V2.5 - Quality per $ 217.1 pts/$
  10. #10 Qwen: Qwen3.5-9B - Quality per $ 193.8 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.

01Ling-3.0-flash1200.0pts/$Quality 37.8 · $0.03/1M
02inclusionAI: Ling-2.6-flash946.7pts/$Quality 14.2 · $0.02/1M
03Z.ai: GLM 5.2 (batch)489.3pts/$Quality 52.6 · $0.11/1M
04DeepSeek: DeepSeek V4 Flash 0423460.4pts/$Quality 51.8 · $0.11/1M
05Tencent: Hy3 preview423.1pts/$Quality 42.2 · $0.10/1M
06OpenAI: gpt-oss-120b343.1pts/$Quality 24.1 · $0.07/1M
07OpenAI: gpt-oss-20b (free)276.4pts/$Quality 15.2 · $0.05/1M
08OpenAI: GPT-5.6 Luna (batch)232.4pts/$Quality 52.3 · $0.22/1M
09Xiaomi: MiMo-V2.5217.1pts/$Quality 38.0 · $0.18/1M
10Qwen: Qwen3.5-9B193.8pts/$Quality 21.8 · $0.11/1M
11Google: Gemma 4 26B A4B (free)189.8pts/$Quality 26.1 · $0.14/1M
12Google: Gemma 4 31B (free)185.6pts/$Quality 29.7 · $0.16/1M
13NVIDIA: Nemotron 3 Nano 30B A3B (free)165.7pts/$Quality 14.5 · $0.09/1M
14inclusionAI: Ring-2.6-1T146.4pts/$Quality 31.1 · $0.21/1M
15DeepSeek: DeepSeek V3.2108.0pts/$Quality 32.6 · $0.30/1M
85 eligible models, sorted by quality per $
#ModelQualityPrice/1MQuality per $
01Ling-3.0-flash37.8$0.031200.0 pts/$
02inclusionAI: Ling-2.6-flash14.2$0.02946.7 pts/$
03Z.ai: GLM 5.2 (batch)52.6$0.11489.3 pts/$
04DeepSeek: DeepSeek V4 Flash 042351.8$0.11460.4 pts/$
05Tencent: Hy3 preview42.2$0.10423.1 pts/$
06OpenAI: gpt-oss-120b24.1$0.07343.1 pts/$
07OpenAI: gpt-oss-20b (free)15.2$0.05276.4 pts/$
08OpenAI: GPT-5.6 Luna (batch)52.3$0.22232.4 pts/$
09Xiaomi: MiMo-V2.538.0$0.18217.1 pts/$
10Qwen: Qwen3.5-9B21.8$0.11193.8 pts/$
11Google: Gemma 4 26B A4B (free)26.1$0.14189.8 pts/$
12Google: Gemma 4 31B (free)29.7$0.16185.6 pts/$
13NVIDIA: Nemotron 3 Nano 30B A3B (free)14.5$0.09165.7 pts/$
14inclusionAI: Ring-2.6-1T31.1$0.21146.4 pts/$
15DeepSeek: DeepSeek V3.232.6$0.30108.0 pts/$
16Nex AGI: Nex-N2-Pro41.7$0.4495.3 pts/$
17Qwen: Qwen3.6 35B A3B32.1$0.3688.6 pts/$
18MiniMax: MiniMax M3 (batch)45.4$0.5286.5 pts/$
19OpenAI: GPT-5.4 Nano (batch)39.7$0.4685.8 pts/$
20DeepSeek: DeepSeek V4 Pro45.3$0.5483.3 pts/$
21Xiaomi: MiMo-V2.5-Pro42.9$0.5478.9 pts/$
22Mistral: Mistral Small 419.7$0.2675.0 pts/$
23MiniMax: MiniMax M2.738.9$0.5274.1 pts/$
24Qwen: Qwen3 Coder Next21.3$0.2973.4 pts/$
25StepFun: Step 3.7 Flash30.9$0.4470.6 pts/$
26Qwen: Qwen3.7 Plus39.4$0.5670.4 pts/$
27Qwen: Qwen3.5-35B-A3B24.3$0.3568.5 pts/$
28DeepSeek: DeepSeek V3.1 Terminus30.6$0.4567.6 pts/$
29Z.ai: GLM 4.629.3$0.4565.1 pts/$
30Thinking Machines: Inkling Small41.2$0.6464.6 pts/$
31Kwaipilot: KAT-Coder-Pro V233.9$0.5264.6 pts/$
32Inception: Mercury 221.9$0.3858.4 pts/$
33NVIDIA: Nemotron 3 Super (free)25.7$0.4557.1 pts/$
34Mistral: Ministral 3 14B 251211.2$0.2056.0 pts/$
35Upstage: Solar Pro 314.5$0.2655.2 pts/$
36Arcee AI: Trinity Large Thinking18.6$0.3849.3 pts/$
37Z.ai: GLM 4.734.5$0.7446.8 pts/$
38Google: Gemini 3.1 Flash Lite Preview25.6$0.5645.5 pts/$
39Google: Gemini 3.5 Flash Lite (batch)37.4$0.8544.0 pts/$
40MoonshotAI: Kimi K2.645.1$1.0443.2 pts/$
41Qwen: Qwen3.5-122B-A10B32.8$0.8240.1 pts/$
42Qwen: Qwen3.5 397B A17B34.3$0.8839.1 pts/$
43OpenAI: GPT-5 Mini (batch)25.8$0.6937.5 pts/$
44SpaceXAI: Grok Build 0.140.7$1.2532.6 pts/$
45DeepSeek: DeepSeek V3 032415.2$0.4831.5 pts/$
46MoonshotAI: Kimi K2.7 Code (batch)43.0$1.4030.7 pts/$
47NVIDIA: Nemotron 3 Ultra (free)38.3$1.3528.4 pts/$
48Z.ai: GLM 5.141.0$1.4628.0 pts/$
49Qwen: Qwen3.6 27B37.7$1.3527.9 pts/$
50Qwen: Qwen3 235B A22B Thinking 250719.9$0.7526.6 pts/$
51Meta: Muse Spark 1.153.2$2.0026.6 pts/$
52OpenAI: GPT-5.6 Terra (batch)56.6$2.2525.2 pts/$
53Thinking Machines: Inkling (batch)42.3$1.7324.5 pts/$
54SpaceXAI: Grok 4.337.9$1.5624.3 pts/$
55OpenAI: GPT-5.4 Mini (batch)40.9$1.6924.2 pts/$
56Amazon: Nova 2 Lite18.4$0.8521.6 pts/$
57Mistral: Mistral Large 3 251215.9$0.7521.2 pts/$
58OpenAI: GPT-4.1 Mini (batch)14.8$0.7021.1 pts/$
59Qwen: Qwen3.7 Max46.7$2.2121.1 pts/$
60Qwen: Qwen3 30B A3B Thinking 250714.6$0.7519.5 pts/$
61Qwen: Qwen3.8 Max58.1$3.0019.4 pts/$
62SpaceXAI: Grok 4.555.8$3.0018.6 pts/$
63Mistral: Mistral Medium 3.114.7$0.8018.4 pts/$
64Google: Gemini 3.6 Flash (batch)51.6$3.0017.2 pts/$
65DeepSeek: R118.6$1.1516.2 pts/$
66MoonshotAI: Kimi K2 Thinking17.2$1.0816.0 pts/$
67Google: Gemini 3.5 Flash (batch)52.0$3.3815.4 pts/$
68Anthropic: Claude Haiku 4.5 (batch)29.9$2.0014.9 pts/$
69Anthropic: Claude Sonnet 5 (batch)55.3$4.0013.8 pts/$
70OpenAI: GPT-5.1 (batch)37.5$3.4410.9 pts/$
71Google: Gemini 3.1 Pro Preview (batch)47.7$4.5010.6 pts/$
72OpenAI: GPT-5 (batch)35.3$3.4410.3 pts/$
73MoonshotAI: Kimi K359.7$6.0010.0 pts/$
74OpenAI: GPT-5.4 (batch)53.1$5.639.4 pts/$
75OpenAI: o3 Mini High (batch)15.7$1.938.2 pts/$
76Anthropic: Claude Sonnet 4.6 (batch)48.4$6.008.1 pts/$
77Google: Gemini 2.5 Pro (batch)25.9$3.447.5 pts/$
78Claude Opus 5 (batch)63.1$10.006.3 pts/$
79Anthropic: Claude Sonnet 4.5 (batch)37.4$6.006.2 pts/$
80Anthropic: Claude Opus 4.8 (batch)57.3$10.005.7 pts/$
81Anthropic: Claude Opus 4.7 (batch)55.0$10.005.5 pts/$
82OpenAI: GPT-5.6 Sol (batch)60.9$11.255.4 pts/$
83OpenAI: GPT-5.5 (batch)56.3$11.255.0 pts/$
84Anthropic: Claude Sonnet 429.8$6.005.0 pts/$
85Anthropic: Claude Fable 5 (batch)62.1$20.003.1 pts/$

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 August 9, 2026.

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

Methodology: smophy.ai/benchmark/methodology

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