IQ of SI
English ▾

Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

τ²-bench Airline (OpenRouter run): AI model results

τ²-bench Airline (OpenRouter run) is a Agents benchmark run by OpenRouter. 117 models in our data have a published result.

It is part of the SI-IQ index (loading k = 0.41, chance level 0%).

Evaluator
OpenRouter
Benchmark home page
openrouter.ai/benchmarks/tau2-bench-airline

Results

Source
1 MiMo-V2.6 Pro Xiaomi Corp79.8%131117–144 2 too little data Sep 2026OpenRouter benchmark datasets
2 Claude Fable 5 Anthropic79.6%138134–141 8 Jun 2026OpenRouter benchmark datasets
3 Claude Fable 5.1 Anthropic79.1%140136–143 8 Sep 2026OpenRouter benchmark datasets
4 DeepSeek-V4-Proopen DeepSeek78.9%117113–120 9 Apr 2026OpenRouter benchmark datasets
5 Gemini 4 Argon Google DeepMind78.7%140137–143 8 Sep 2026OpenRouter benchmark datasets
6 Gemini 3.7 Flash Google DeepMind78.3%131128–134 8 Aug 2026OpenRouter benchmark datasets
7 Qwen3.5 397B-A17Bopen Alibaba78.1%114109–118 5 Feb 2026OpenRouter benchmark datasets
8 GLM-5.3open Z.ai (Zhipu AI)78.1%125122–128 8 Aug 2026OpenRouter benchmark datasets
9 Muse Spark Openopen Meta AI78.0%127124–130 6 Oct 2026OpenRouter benchmark datasets
10 Tencent Hy4 previewopen Tencent77.8%129115–143 2 too little data Aug 2026OpenRouter benchmark datasets
11 Claude Opus 4.8 Anthropic77.8%132129–135 8 May 2026OpenRouter benchmark datasets
12 DeepSeek V4 Flash 0731open DeepSeek77.7%124121–127 8 Jul 2026OpenRouter benchmark datasets
13 Claude Opus 4.7 Anthropic77.6%127124–130 9 Apr 2026OpenRouter benchmark datasets
14 DeepSeek-V4-Flashopen DeepSeek77.6%129116–143 2 too little data Apr 2026OpenRouter benchmark datasets
15 Claude Sonnet 5.5 Anthropic77.5%140137–143 8 Sep 2026OpenRouter benchmark datasets
16 Claude Opus 5 Anthropic77.3%136133–140 8 Jul 2026OpenRouter benchmark datasets
17 Claude Opus 4.5 Anthropic77.0%115111–118 10 Nov 2025OpenRouter benchmark datasets
18 DeepSeek V4 Pro 0813open DeepSeek76.8%128125–131 8 Aug 2026OpenRouter benchmark datasets
19 Kimi K2.6open Moonshot76.7%121118–124 9 Apr 2026OpenRouter benchmark datasets
20 Claude Opus 4.6 Anthropic76.4%123120–126 9 Feb 2026OpenRouter benchmark datasets
21 Qwen3.6 27Bopen Alibaba76.3%115110–119 5 Apr 2026OpenRouter benchmark datasets
22 GLM-5.3-Flashopen Z.ai (Zhipu AI)76.2%120117–124 7 Aug 2026OpenRouter benchmark datasets
23 Claude Sonnet 5 Anthropic76.0%126123–129 8 Jun 2026OpenRouter benchmark datasets
24 MiMo-V2.6 Flash Xiaomi Corp76.0%11299–125 2 too little data Sep 2026OpenRouter benchmark datasets
25 Qwen 3.8 27Bopen Alibaba75.9%120106–133 2 too little data Aug 2026OpenRouter benchmark datasets
26 GPT-5.1 OpenAI75.8%120115–125 7 Nov 2025OpenRouter benchmark datasets
27 Claude Haiku 5.5 Anthropic75.8%129126–132 8 Oct 2026OpenRouter benchmark datasets
28 Gemma 4 31B ITopen Google DeepMind75.7%10498–110 4 too little data Apr 2026OpenRouter benchmark datasets
29 Claude Opus 5.5 Anthropic75.6%144141–148 8 Sep 2026OpenRouter benchmark datasets
30 Gemini 3 Flash Google DeepMind75.3%122119–125 9 Dec 2025OpenRouter benchmark datasets
31 GPT-5.3 Codex OpenAI75.3%122108–136 2 too little data Feb 2026OpenRouter benchmark datasets
32 Claude Sonnet 4.5 Anthropic75.3%110107–113 11 Sep 2025OpenRouter benchmark datasets
33 GPT-5.5 OpenAI75.0%138135–141 9 Apr 2026OpenRouter benchmark datasets
34 Claude Sonnet 4.6 Anthropic74.9%113108–118 7 Feb 2026OpenRouter benchmark datasets
35 Grok 4.6 xAI74.8%126123–129 8 Aug 2026OpenRouter benchmark datasets
36 Qwen3.5-122B-A10Bopen Alibaba74.7%112103–121 3 too little data Feb 2026OpenRouter benchmark datasets
37 DeepSeek V4.1 Flashopen DeepSeek74.5%128125–131 8 Sep 2026OpenRouter benchmark datasets
38 Qwen 3.6 35B-A3Bopen Alibaba74.5%111107–115 5 Apr 2026OpenRouter benchmark datasets
39 MiMo-V2.5-Proopen Xiaomi Corp74.4%121108–135 2 too little data Apr 2026OpenRouter benchmark datasets
40 GLM-5.1open Z.ai (Zhipu AI)74.3%116112–120 7 Apr 2026OpenRouter benchmark datasets
41 Gemini 3.1 Pro Google DeepMind74.2%127124–130 9 Feb 2026OpenRouter benchmark datasets
42 GLM-5open Z.ai (Zhipu AI)74.2%112105–118 4 too little data Feb 2026OpenRouter benchmark datasets
43 MiniMax-M3open MiniMax73.9%108102–114 5 Jun 2026OpenRouter benchmark datasets
44 Kimi K2.7 Codeopen Moonshot73.8%118115–122 7 Jun 2026OpenRouter benchmark datasets
45 MiMo-V2.5open Xiaomi Corp73.7%117104–131 2 too little data Apr 2026OpenRouter benchmark datasets
46 Qwen3.5-35B-A3Bopen Alibaba73.5%106100–112 3 too little data Feb 2026OpenRouter benchmark datasets
47 Gemini 3.5 Flash-Lite Google DeepMind73.5%109106–113 7 Jul 2026OpenRouter benchmark datasets
48 Kimi K3open Moonshot73.5%127124–130 8 Jul 2026OpenRouter benchmark datasets
49 Gemini 3.8 Flash Google DeepMind73.5%130127–133 8 Sep 2026OpenRouter benchmark datasets
50 GLM-4.6open Z.ai (Zhipu AI), Tsinghua University73.4%117106–128 3 too little data Sep 2025OpenRouter benchmark datasets
51 Gemini 3.5 Flash Google DeepMind73.3%126123–129 9 May 2026OpenRouter benchmark datasets
52 GPT-5.6 Sol OpenAI73.3%140137–143 8 Jul 2026OpenRouter benchmark datasets
53 GPT-5.4 OpenAI73.2%131128–133 9 Mar 2026OpenRouter benchmark datasets
54 Kimi K2.5open Moonshot72.8%119112–125 5 Jan 2026OpenRouter benchmark datasets
55 GPT-5.2 OpenAI72.7%125122–128 10 Dec 2025OpenRouter benchmark datasets
56 Qwen3.7-Plus Alibaba72.7%115110–119 5 Jun 2026OpenRouter benchmark datasets
57 GPT-5.6 Luna OpenAI72.3%130127–133 8 Jul 2026OpenRouter benchmark datasets
58 MiniMax-M2.7open MiniMax72.0%120107–134 2 too little data Mar 2026OpenRouter benchmark datasets
59 Gemini 3.6 Flash Google DeepMind72.0%125122–128 8 Jul 2026OpenRouter benchmark datasets
60 Nemotron 3 Ultraopen Nvidia72.0%114108–120 4 too little data Jun 2026OpenRouter benchmark datasets
61 Qwen3.7-Max Alibaba72.0%125122–128 9 May 2026OpenRouter benchmark datasets
62 DeepSeek-V3.2open DeepSeek71.9%114101–127 2 too little data Dec 2025OpenRouter benchmark datasets
63 GLM-5.2open Z.ai (Zhipu AI)71.7%121118–124 9 Jun 2026OpenRouter benchmark datasets
64 GPT-5.6 Terra OpenAI71.5%134131–137 8 Jul 2026OpenRouter benchmark datasets
65 GPT-5 mini OpenAI71.2%115112–118 11 Aug 2025OpenRouter benchmark datasets
66 GPT-5 OpenAI70.7%121118–124 11 Aug 2025OpenRouter benchmark datasets
67 GLM-4.7open Z.ai (Zhipu AI)70.4%112107–118 5 Dec 2025OpenRouter benchmark datasets
68 GPT-6 Sol OpenAI70.2%140137–144 8 Sep 2026OpenRouter benchmark datasets
69 Qwen3.8 Flash Alibaba70.0%125111–138 2 too little data Aug 2026OpenRouter benchmark datasets
70 Kimi K2 Thinkingopen Moonshot69.5%11299–126 2 too little data Nov 2025OpenRouter benchmark datasets
71 DeepSeek-V3.2-Expopen DeepSeek69.3%112103–121 4 too little data Sep 2025OpenRouter benchmark datasets
72 MiniMax-M2.5open MiniMax69.1%118105–132 2 too little data Feb 2026OpenRouter benchmark datasets
73 glm-4.7-flash —68.3%9488–100 3 too little data —OpenRouter benchmark datasets
74 GPT-6.1 Sol OpenAI68.2%148144–152 8 Sep 2026OpenRouter benchmark datasets
75 GLM-4.5-Airopen Z.ai (Zhipu AI), Tsinghua University68.0%11491–137 1 too little data Jul 2025OpenRouter benchmark datasets
76 GPT-6 Luna OpenAI68.0%130127–133 8 Sep 2026OpenRouter benchmark datasets
77 MiniMax-M2.1open MiniMax67.8%120106–133 2 too little data Dec 2025OpenRouter benchmark datasets
78 GPT-6 Astra OpenAI67.7%150146–153 8 Sep 2026OpenRouter benchmark datasets
79 Inklingopen Thinking Machines67.6%114110–117 7 Jul 2026OpenRouter benchmark datasets
80 Claude Haiku 4.5 Anthropic66.6%10499–108 7 Oct 2025OpenRouter benchmark datasets
81 GPT-5.4 Nano OpenAI65.2%118115–121 8 Mar 2026OpenRouter benchmark datasets
82 Qwen3.5-9Bopen Alibaba65.0%10195–107 3 too little data Feb 2026OpenRouter benchmark datasets
83 Claude Sonnet 4 Anthropic64.0%9793–101 5 May 2025OpenRouter benchmark datasets
84 Kimi K2 (Sep 2025)open Moonshot63.7%10592–118 2 too little data Sep 2025OpenRouter benchmark datasets
85 gpt-oss-120bopen OpenAI63.3%10699–112 5 Aug 2025OpenRouter benchmark datasets
86 Qwen3-235B-A22B-Thinking (Jul 2025)open Alibaba62.7%111105–118 5 Jul 2025OpenRouter benchmark datasets
87 GPT-5.4 Mini OpenAI62.2%117113–120 8 Mar 2026OpenRouter benchmark datasets
88 Inkling-Smallopen Thinking Machines60.8%118115–122 7 Jul 2026OpenRouter benchmark datasets
89 qwen3-coder-next —57.6%10390–116 2 too little data Feb 2026OpenRouter benchmark datasets
90 Gemma 4 26B A4Bopen Google DeepMind57.3%106100–112 3 too little data Apr 2026OpenRouter benchmark datasets
91 Gemini 2.5 Pro (Jun 2025) Google DeepMind56.2%108104–112 7 Jun 2025OpenRouter benchmark datasets
92 Gemini 2.5 Flash (Jun 2025) Google DeepMind55.1%10291–113 3 too little data Jun 2025OpenRouter benchmark datasets
93 GPT-4.1 OpenAI50.8%9187–94 10 Apr 2025OpenRouter benchmark datasets
94 DeepSeek-V3.1-Terminusopen DeepSeek48.3%10289–115 2 too little data Sep 2025OpenRouter benchmark datasets
95 Gemma 3 12Bopen Google DeepMind48.0%7366–79 4 too little data Mar 2025OpenRouter benchmark datasets
96 DeepSeek-R1 (May 2025)open DeepSeek47.9%104100–109 4 too little data May 2025OpenRouter benchmark datasets
97 DeepSeek-V3.1open DeepSeek47.2%10087–113 2 too little data Aug 2025OpenRouter benchmark datasets
98 gpt-oss-20bopen OpenAI46.7%9589–101 3 too little data Aug 2025OpenRouter benchmark datasets
99 Qwen3-32Bopen Alibaba45.2%9589–100 5 Apr 2025OpenRouter benchmark datasets
100 GPT-5 nano OpenAI45.1%105102–109 10 Aug 2025OpenRouter benchmark datasets
101 GPT-4.1 mini OpenAI44.3%9188–95 10 Apr 2025OpenRouter benchmark datasets
102 GPT-4o (May 2024) OpenAI44.0%7066–75 4 too little data May 2024OpenRouter benchmark datasets
103 DeepSeek-V3 (Mar 2025)open DeepSeek43.4%8581–90 4 too little data Mar 2025OpenRouter benchmark datasets
104 Qwen3-Coder-480B-A35Bopen Alibaba43.3%8572–98 2 too little data Jul 2025OpenRouter benchmark datasets
105 Llama 4 Maverickopen Meta AI43.1%8177–85 6 Apr 2025OpenRouter benchmark datasets
106 GPT-4o (Aug 2024) OpenAI43.0%7368–77 8 Aug 2024OpenRouter benchmark datasets
107 Qwen3-30B-A3Bopen Alibaba42.3%9488–100 3 too little data Apr 2025OpenRouter benchmark datasets
108 Qwen3-14Bopen Alibaba41.3%9387–99 4 too little data Apr 2025OpenRouter benchmark datasets
109 Mistral Small 4open Mistral AI41.1%9683–108 2 too little data Mar 2026OpenRouter benchmark datasets
110 DeepSeek-V3open DeepSeek40.5%7773–82 4 too little data Dec 2024OpenRouter benchmark datasets
111 Qwen3-235B-A22B-Instruct (Jul 2025)open Alibaba39.6%9685–107 3 too little data Jul 2025OpenRouter benchmark datasets
112 Qwen3-30B-A3B-Instruct (Jul 2025)open Alibaba37.0%9186–97 4 too little data Jul 2025OpenRouter benchmark datasets
113 Llama 3.3 70Bopen Meta AI31.3%6661–71 5 Dec 2024OpenRouter benchmark datasets
114 GPT-4o mini OpenAI28.0%6864–73 9 Jul 2024OpenRouter benchmark datasets
115 Qwen2.5-72Bopen Alibaba25.0%7268–77 4 too little data Sep 2024OpenRouter benchmark datasets
116 Qwen2.5-7Bopen Alibaba16.7%5141–60 3 too little data Sep 2024OpenRouter benchmark datasets
117 GPT-4.1 nano OpenAI11.8%7672–80 8 Apr 2025OpenRouter benchmark datasets

Data sources: Aider polyglot leaderboard data (Apache-2.0); Arena leaderboard dataset on Hugging Face (CC BY 4.0); Berkeley Function Calling Leaderboard, Gorilla project (Apache-2.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..