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 November 7, 2026, OpenAI: gpt-oss-120b (batch) ranks #1 for best value at quality per $ 692.5 pts/$.

  1. #1 OpenAI: gpt-oss-120b (batch) - Quality per $ 692.5 pts/$
  2. #2 inclusionAI: Ling 3.1 Flash - Quality per $ 608.9 pts/$
  3. #3 Upstage: Solar Mini 4 - Quality per $ 275.4 pts/$
  4. #4 Anthropic: Claude Haiku 5.5 (batch) - Quality per $ 182.5 pts/$
  5. #5 Inception: Mercury 2.5 - Quality per $ 182.2 pts/$
  6. #6 OpenAI: gpt-oss-20b (batch) - Quality per $ 163.6 pts/$
  7. #7 Xiaomi: MiMo-V2.6-Flash - Quality per $ 152.6 pts/$
  8. #8 OpenAI: GPT-6 Luna (batch) - Quality per $ 139.5 pts/$
  9. #9 Z.ai: GLM 5.3 Flash (batch) - Quality per $ 117.1 pts/$
  10. #10 MiniMax: MiniMax M3.1 Flash - Quality per $ 110.9 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.

01OpenAI: gpt-oss-120b (batch)692.5pts/$Quality 11.6 · $0.02/1M
02inclusionAI: Ling 3.1 Flash608.9pts/$Quality 41.1 · $0.07/1M
03Upstage: Solar Mini 4275.4pts/$Quality 24.1 · $0.09/1M
04Anthropic: Claude Haiku 5.5 (batch)182.5pts/$Quality 36.5 · $0.20/1M
05Inception: Mercury 2.5182.2pts/$Quality 12.3 · $0.07/1M
06OpenAI: gpt-oss-20b (batch)163.6pts/$Quality 9.0 · $0.05/1M
07Xiaomi: MiMo-V2.6-Flash152.6pts/$Quality 26.7 · $0.18/1M
08OpenAI: GPT-6 Luna (batch)139.5pts/$Quality 27.9 · $0.20/1M
09Z.ai: GLM 5.3 Flash (batch)117.1pts/$Quality 27.8 · $0.24/1M
10MiniMax: MiniMax M3.1 Flash110.9pts/$Quality 29.1 · $0.26/1M
11DeepSeek: DeepSeek V4.1 Flash (batch)109.0pts/$Quality 28.6 · $0.26/1M
12Upstage: Solar Pro 4107.4pts/$Quality 28.2 · $0.26/1M
13NVIDIA: Nemotron 3 Nano 30B A3B84.8pts/$Quality 8.9 · $0.10/1M
14NVIDIA: Nemotron 3 Super81.9pts/$Quality 12.8 · $0.16/1M
15Z.ai: GLM 5.3 (batch)78.8pts/$Quality 31.7 · $0.40/1M
96 eligible models, sorted by quality per $
#ModelQualityPrice/1MQuality per $
01OpenAI: gpt-oss-120b (batch)11.6$0.02692.5 pts/$
02inclusionAI: Ling 3.1 Flash41.1$0.07608.9 pts/$
03Upstage: Solar Mini 424.1$0.09275.4 pts/$
04Anthropic: Claude Haiku 5.5 (batch)36.5$0.20182.5 pts/$
05Inception: Mercury 2.512.3$0.07182.2 pts/$
06OpenAI: gpt-oss-20b (batch)9.0$0.05163.6 pts/$
07Xiaomi: MiMo-V2.6-Flash26.7$0.18152.6 pts/$
08OpenAI: GPT-6 Luna (batch)27.9$0.20139.5 pts/$
09Z.ai: GLM 5.3 Flash (batch)27.8$0.24117.1 pts/$
10MiniMax: MiniMax M3.1 Flash29.1$0.26110.9 pts/$
11DeepSeek: DeepSeek V4.1 Flash (batch)28.6$0.26109.0 pts/$
12Upstage: Solar Pro 428.2$0.26107.4 pts/$
13NVIDIA: Nemotron 3 Nano 30B A3B8.9$0.1084.8 pts/$
14NVIDIA: Nemotron 3 Super12.8$0.1681.9 pts/$
15Z.ai: GLM 5.3 (batch)31.7$0.4078.8 pts/$
16Qwen: Qwen3.5-9B11.2$0.1958.9 pts/$
17NVIDIA: Nemotron 3.5 Super VL (free)13.6$0.2457.3 pts/$
18Tencent: Hy434.6$0.6355.3 pts/$
19Xiaomi: MiMo-V2.6-Pro29.9$0.5455.0 pts/$
20OpenAI: GPT-4.1 Nano (batch)9.6$0.1754.9 pts/$
21NVIDIA: Nemotron 3.5 Lightning (free)5.5$0.1053.7 pts/$
22OpenAI: GPT-5.6 Luna (batch)23.8$0.4552.9 pts/$
23Google: Gemma 3 12B3.8$0.0750.7 pts/$
24Mistral: Ministral 3 3B 25124.8$0.1048.0 pts/$
25IBM: Granite 4.2 8B5.1$0.1147.4 pts/$
26MiniMax: MiniMax M2.522.8$0.5243.4 pts/$
27Reflection: Beam 1.0 501B A23B17.7$0.4737.3 pts/$
28Mistral: Ministral 3 8B 25125.5$0.1536.7 pts/$
29MiniMax: MiniMax M3 (batch)18.9$0.5236.0 pts/$
30Qwen: Qwen3.8 27B (batch)20.1$0.5834.6 pts/$
31Google: Gemma 3 27B4.9$0.1533.2 pts/$
32Qwen: Qwen3 Coder Next9.2$0.2931.7 pts/$
33Inception: Mercury 211.5$0.3830.7 pts/$
34Mistral: Ministral 3 14B 25126.0$0.2030.0 pts/$
35Upstage: Solar Pro 37.8$0.2629.7 pts/$
36Arcee AI: Trinity Large Thinking10.8$0.3927.9 pts/$
37Qwen: Qwen3.5-27B22.9$0.8427.1 pts/$
38OpenAI: GPT-6.1 Terra (batch)51.3$2.0025.6 pts/$
39Mistral: Mistral Large 426.1$1.0524.9 pts/$
40OpenAI: GPT-5 Mini (batch)16.8$0.6924.4 pts/$
41Google: Gemini 3 Flash Preview (batch)26.3$1.1323.4 pts/$
42Amazon: Nova 2 Lite18.4$0.8521.6 pts/$
43OpenAI: GPT-4.1 Mini (batch)14.8$0.7021.1 pts/$
44MoonshotAI: Kimi K2 Thinking22.0$1.0820.5 pts/$
45Thinking Machines: Inkling Small (batch)12.9$0.6420.2 pts/$
46StepFun: Step 5 Preview28.5$1.4220.0 pts/$
47DeepSeek: DeepSeek V3 03249.7$0.5019.3 pts/$
48Google: Gemini 3.8 Flash (batch)30.8$1.6518.7 pts/$
49DeepSeek: DeepSeek V4 Pro 042323.1$1.2518.4 pts/$
50Meta: Muse Spark 1.336.6$2.0018.3 pts/$
51Z.ai: GLM 527.9$1.5518.0 pts/$
52Qwen: Qwen3.8 Max53.4$3.0017.8 pts/$
53Google: Gemma 4 31B (free)4.4$0.2517.6 pts/$
54SpaceXAI: Grok 4.2025.7$1.5616.4 pts/$
55Mistral: Mistral Small 44.3$0.2616.4 pts/$
56Z.ai: GLM 5 Turbo26.6$1.9014.0 pts/$
57Google: Gemini 3.5 Flash Lite (batch)11.7$0.8513.8 pts/$
58Qwen: Qwen3 Max Thinking21.3$1.5613.7 pts/$
59OpenAI: GPT-6.1 Sol (batch)54.6$4.0013.6 pts/$
60Anthropic: Claude Sonnet 5.5 (batch)54.5$4.0013.6 pts/$
61Qwen: Qwen3 30B A3B Thinking 25079.8$0.7513.1 pts/$
62Google: Gemini 4 Argon (batch)50.4$4.0012.6 pts/$
63Meta: Muse Spark Open24.9$2.0012.4 pts/$
64Mistral: Mistral Large 3 25129.3$0.7512.4 pts/$
65Z.ai: GLM 5V Turbo23.5$1.9012.4 pts/$
66Qwen: Qwen3.6 Max Preview28.4$2.3112.3 pts/$
67Meta: Muse Glimmer 30B (batch)6.3$0.5212.0 pts/$
68SpaceXAI: Grok 4.7 (batch)35.5$3.0011.8 pts/$
69MoonshotAI: Kimi K3.1 Pro46.5$4.0011.6 pts/$
70Mistral: Mistral Medium 3.19.2$0.8011.5 pts/$
71NVIDIA: Nemotron 3 Ultra (free)11.8$1.0511.2 pts/$
72OpenAI: GPT-6 Sol (batch)44.2$4.0011.0 pts/$
73Google: Gemini 3.1 Flash Lite Preview6.2$0.5611.0 pts/$
74Mistral: Devstral 2 25128.6$0.8010.8 pts/$
75Qwen: Qwen3 235B A22B Thinking 250712.7$1.2110.5 pts/$
76SpaceXAI: Grok 4.6 (batch)31.0$3.0010.3 pts/$
77DeepSeek: R111.4$1.159.9 pts/$
78Anthropic: Claude Opus 5.5 (batch)59.1$8.007.4 pts/$
79OpenAI: GPT-5.6 Terra (batch)32.3$4.507.2 pts/$
80Thinking Machines: Inkling12.5$1.767.1 pts/$
81OpenAI: GPT-5.1-Codex23.7$3.446.9 pts/$
82OpenAI: GPT-5.3-Codex32.5$4.816.8 pts/$
83OpenAI: GPT-5.2 (batch)30.4$4.816.3 pts/$
84OpenAI: GPT-5.2-Codex28.5$4.815.9 pts/$
85OpenAI: o3 Mini High11.0$1.935.7 pts/$
86Meta: Muse Wonder43.6$8.005.4 pts/$
87Google: Gemini 2.5 Pro16.1$3.444.7 pts/$
88Anthropic: Claude Opus 5 (batch)44.2$10.004.4 pts/$
89MoonshotAI: Kimi K3 (batch)17.4$4.144.2 pts/$
90Anthropic: Claude Haiku 4.5 (batch)7.4$2.003.7 pts/$
91Anthropic: Claude Opus 4.6 (batch)31.9$10.003.2 pts/$
92Anthropic: Claude Opus 4.5 (batch)29.1$10.002.9 pts/$
93OpenAI: GPT-6 Astra (batch)56.9$20.002.8 pts/$
94Anthropic: Claude Fable 5.1 (batch)50.0$20.002.5 pts/$
95Anthropic: Claude Opus 4.1 (batch)22.8$30.000.8 pts/$
96OpenAI: o3 Pro21.9$35.000.6 pts/$

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 November 7, 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.