All General Coding Reasoning Multimodal Safety Specialized Agentic Language Long Context Speed Text-to-Image Image Editing Text-to-Video Image-to-Video

Which AI is best for your task?

4495 models · 84 benchmarks · Pick a category to find the right model

General 518 models · 6 benchmarks
1
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) 82.5
2
GPT-5.6 Sol (max) 82.0
3
GPT-5.6 Sol (xhigh) 78.1

Best value: MiniMax: MiniMax M3 at $1.50/M · 32x more per $

Coding 239 models · 4 benchmarks
1
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) 96.9
2
Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) 94.5
3
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) 92.0

Best value: grok-4-fast-reasoning at $0.70/M · 79x more per $

Reasoning 172 models · 10 benchmarks
1
Grok 4 94.8
2
GPT-5 (high) 94.5
3
GPT-5 (medium) 93.3

Best value: Qwen3 32B (Reasoning) at $0.36/M · 40x more per $

Multimodal 87 models · 1 benchmarks
1
gemini-3-pro 100.0
2
Google: Gemini 2.5 ProRetiring 87.0
3
gemini-2.5-flash-preview-09-2025 84.3

Best value: Qwen: Qwen3 VL 235B A22B Instruct at $2.11/M

Safety 2839 models · 1 benchmarks
1
Meta: Llama 3.3 70B Instruct 100.0
2
MaziyarPanahi/calme-2.1-qwen2.5-72b 96.3
3
Meta: Llama 3.1 70B Instruct 96.3

Best value: Meta: Llama 3.1 70B Instruct at $0.80/M · 66% more per $

Agentic 15 models · 10 benchmarks
1
Anthropic: Claude Opus 4.5 81.6
2
OpenAI: GPT-5.2 81.1
3
Anthropic: Claude Sonnet 4.5 80.5

Best value: Z.ai: GLM 5 at $2.52/M · 804% more per $

Long Context 6 models · 2 benchmarks
1
grok-4-1-fast-reasoning 82.9
2
Grok 4 71.6
3
Grok 4.1 Fast (Non-reasoning) 51.9

Best value: Microsoft: Phi 4 at $0.21/M

Speed 180 models · 9 benchmarks
1
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) 90.5
2
Google: Gemini 2.5 Flash LiteRetiring 90.3
3
Inception: Mercury 2 88.6

Best value: Amazon: Nova Micro 1.0 at $0.18/M · 851% more per $

Text-to-Image 10 models · 2 benchmarks
1
Google: Nano Banana Pro (Gemini 3 Pro Image) 91.8
2
FLUX.2 [flex] 72.9
3
Seedream 4.5 71.5

Best value: FLUX.2 [pro] at $0.030/image · 243% more per $

Image Editing 69 models · 1 benchmarks
1
GPT Image 2.5 Sunburst (max) 100.0
2
GPT Image 2.5 Flare (max) 96.4
3
MAI-Image-2.6 91.9

Best value: Muse Image at $0.010/image · 17x more per $

Text-to-Video 31 models · 1 benchmarks
1
Wan 3.0 100.0
2
MiniMax H3 (768p) 96.1
3
Minimax H3 Max (Based on MiniMax H3) 94.9

Best value: Grok Imagine Video 1.5 Lite at $0.030/s · 78% more per $

Image-to-Video 76 models · 1 benchmarks
1
Gemini Omni Flash 100.0
2
Bach 1.0 Pro 98.7
3
Wan 3.0 98.7

Best value: PixVerse V6 at $0.040/s · 137% more per $

Specialized 3 benchmarks Language 1 benchmarks

Access this data

JSON GET /api/v1 
[
  {
    "category": "general",
    "top_model": "Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)",
    "score": 82.5,
    "best_value": {
      "model": "MiniMax: MiniMax M3",
      "cost": 1.5,
      "cost_unit": "million_tokens",
      "value": 46.7
    }
  },
  {
    "category": "coding",
    "top_model": "Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)",
    "score": 96.9,
    "best_value": {
      "model": "grok-4-fast-reasoning",
      "cost": 0.7,
      "cost_unit": "million_tokens",
      "value": 128.1
    }
  },
  {
    "category": "reasoning",
    "top_model": "Grok 4",
    "score": 94.8,
    "best_value": {
      "model": "Qwen3 32B (Reasoning)",
      "cost": 0.36,
      "cost_unit": "million_tokens",
      "value": 218.9
    }
  }
]
Curl 
$ curl -s https://rightrank.ai/api/v1/rankings/overview.json | jq '.[:3]'
CLI brew install rightrank 
$ rightrank top overview --limit 5
$ rightrank compare claude-opus-4.6 gpt-5.4-pro --category overview
$ rightrank value overview  # best performance per dollar
Claude Code Skill Skill 
# In Claude Code, use the RightRank skill:
/rightrank best model for overview
/rightrank compare top 5 by value
/rightrank cheapest model scoring above 80 on overview