Artificial Analysis Long Context Reasoning

Long Context

Source ↗ Higher is better

Rank	Model	Provider	Score
1	Kimi K3 (max)	Moonshot AI	88.7%
2	StepFun: Step 5 Preview	Stepfun	88.3%
3	Xiaomi: MiMo-V2.6-Pro	Xiaomi	86.3%
4	Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	85.3%
5	Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	84.7%
6	Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)	Anthropic	84.7%
7	Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback)	Anthropic	84.7%
8	Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback)	Anthropic	84.3%
9	GPT-5.5 (xhigh)	OpenAI	84.3%
10	GPT-5.5 (high)	OpenAI	84.3%
11	DeepSeek V4.1 Flash (Reasoning, Max Effort)	DeepSeek	84.0%
12	GPT-5.6 Sol (max)	OpenAI	84.0%
13	GPT-6.1 Sol (low)	OpenAI	84.0%
14	Gemini 3.8 Flash (medium)	Google	84.0%
15	Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)	Anthropic	83.7%
16	Muse Wonder Full (Max)	Meta	83.7%
17	GPT-6 Sol (max)	OpenAI	83.7%
18	GPT-5.6 Luna (max)	OpenAI	83.7%
19	GPT-6 Sol (high)	OpenAI	83.7%
20	Upstage: Solar Mini 4	Upstage	83.3%
21	GPT-5.3 Codex (xhigh)	OpenAI	83.3%
22	GPT-6.1 Sol (medium)	OpenAI	83.3%
23	GPT-6 Luna (max)	OpenAI	83.3%
24	Muse Glimmer (high)	Meta	83.3%
25	Gemini 3.7 Flash (medium)	Google	83.0%
26	GPT-6.1 Sol (max)	OpenAI	83.0%
27	Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)	Anthropic	83.0%
28	Muse Spark 1.3 (xhigh)	Meta	83.0%
29	Muse Spark 1.3 (max)	Meta	83.0%
30	MiniMax: MiniMax M3	MiniMax	83.0%
31	GPT-5.6 Terra (max)	OpenAI	83.0%
32	Agnes 2.5 Pro Beta	Sapiens AI	83.0%
33	inclusionAI: Ling 3.1 Flash	inclusionAI	83.0%
34	GPT-5.5 (medium)	OpenAI	83.0%
35	Claude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback)	Anthropic	82.7%
36	Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	82.7%
37	GPT-5.2 (xhigh)	OpenAI	82.7%
38	Claude Haiku 5.5 (Max)	Anthropic	82.7%
39	GPT-5.6 Sol (xhigh)	OpenAI	82.3%
40	GPT-6.1 Sol (high)	OpenAI	82.3%
41	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)	Anthropic	82.3%
42	GPT-6 Sol (medium)	OpenAI	82.3%
43	Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)	Anthropic	82.3%
44	GPT-5.2 Codex (xhigh)	OpenAI	82.3%
45	Claude Sonnet 5 (Adaptive Reasoning, Max Effort)	Anthropic	82.0%
46	Claude Opus 5 (Adaptive Reasoning, Medium Effort)	Anthropic	82.0%
47	GPT-5.4 (xhigh)	OpenAI	82.0%
48	Google: Gemini 3.1 Pro Preview	Google	82.0%
49	Qwen3.8 27B (xhigh)	Alibaba	82.0%
50	GPT-5.6 Sol (high)	OpenAI	81.7%

Access this data

JSON GET /api/v1

[
  {
    "rank": 1,
    "model": "Kimi K3 (max)",
    "provider": "Moonshot AI",
    "score": "88.6666666666667"
  },
  {
    "rank": 2,
    "model": "StepFun: Step 5 Preview",
    "provider": "Stepfun",
    "score": "88.3333333333333"
  },
  {
    "rank": 3,
    "model": "Xiaomi: MiMo-V2.6-Pro",
    "provider": "Xiaomi",
    "score": "86.3333333333333"
  }
]

Curl

$ curl -s https://rightrank.ai/api/v1/rankings/artificial-analysis-long-context-reasoning.json | jq '.[:3]'

CLI brew install rightrank

$ rightrank top artificial-analysis-long-context-reasoning --limit 5
$ rightrank compare claude-opus-4.6 gpt-5.4-pro --category artificial-analysis-long-context-reasoning
$ rightrank value artificial-analysis-long-context-reasoning  # best performance per dollar

Claude Code Skill Skill

# In Claude Code, use the RightRank skill:
/rightrank best model for artificial-analysis-long-context-reasoning
/rightrank compare top 5 by value
/rightrank cheapest model scoring above 80 on artificial-analysis-long-context-reasoning