modelgrep

Best Reasoning LLMs

Quick answer · Updated June 2026

The best LLM for reasoning is Claude Fable 5 — 64.9 intelligence with extended step-by-step thinking. Claude Opus 4.8 (61.4) and Claude Opus 4.7 (57.3) round out the top three.

64.9Intelligence
$10.00Input /M
1MContext

Large language models with extended reasoning / thinking, ranked by intelligence. The best models for complex multi-step reasoning, math and analysis.

  1. 1A
    claude-fable-5
    ReasoningToolsJSON+164.9 intel · $10.00/M · 1M ctx
    64.9
    Intelligence
  2. 2A
    claude-opus-4.8
    ReasoningToolsJSON+161.4 intel · $5.00/M · 58 t/s
    61.4
    Intelligence
  3. 3A
    claude-opus-4.7
    ReasoningToolsJSON+157.3 intel · $5.00/M · 60 t/s
    57.3
    Intelligence
  4. 4O
    gpt-5.5
    ReasoningToolsJSON+156.7 intel · $5.00/M · 37 t/s
    56.7
    Intelligence
  5. 5Q
    qwen3.7-max
    ReasoningToolsJSON56.6 intel · $1.25/M · 39 t/s
    56.6
    Intelligence
  6. 6M
    minimax-m3
    ReasoningToolsJSON+154.7 intel · $0.300/M · 47 t/s
    54.7
    Intelligence
  7. 7X
    mimo-v2.5-pro
    ReasoningToolsJSON53.8 intel · $0.435/M · 32 t/s
    53.8
    Intelligence
  8. 8O
    gpt-5.3-codex
    ReasoningToolsJSON+153.6 intel · $1.75/M · 45 t/s
    53.6
    Intelligence
  9. 9Q
    qwen3.7-plus
    ReasoningToolsJSON+153.3 intel · $0.320/M · 29 t/s
    53.3
    Intelligence
  10. 10X
    grok-4.3
    ReasoningToolsJSON+153.2 intel · $1.25/M · 135 t/s
    53.2
    Intelligence
  11. 11A
    claude-opus-4.6
    ReasoningToolsJSON+152.9 intel · $5.00/M · 46 t/s
    52.9
    Intelligence
  12. 12Q
    qwen3.6-max-preview
    ReasoningToolsJSON51.8 intel · $1.04/M · 48 t/s
    51.8
    Intelligence
  13. 13Q
    qwen3.6-plus
    ReasoningToolsJSON+150.0 intel · $0.325/M · 36 t/s
    50.0
    Intelligence
  14. 14Z
    glm-5
    ReasoningToolsJSON49.8 intel · $0.600/M · 112 t/s
    49.8
    Intelligence
  15. 15M
    minimax-m2.7
    ReasoningToolsJSON49.6 intel · $0.250/M · 334 t/s
    49.6
    Intelligence
  16. 16X
    mimo-v2.5
    ReasoningToolsJSON+249.0 intel · $0.140/M · 49 t/s
    49.0
    Intelligence
  17. 17O
    gpt-5.2-codex
    ReasoningToolsJSON+149.0 intel · $1.75/M · 85 t/s
    49.0
    Intelligence
  18. 18N
    nemotron-3-ultra-550b-a55b:free
    ReasoningTools47.7 intel · Free/M · 64 t/s
    47.7
    Intelligence
  19. 19N
    nemotron-3-ultra-550b-a55b
    ReasoningToolsJSON47.7 intel · $0.500/M · 64 t/s
    47.7
    Intelligence
  20. 20O
    gpt-5.1
    ReasoningToolsJSON+147.7 intel · $1.25/M · 55 t/s
    47.7
    Intelligence
  21. 21Z
    glm-5-turbo
    ReasoningToolsJSON46.8 intel · $1.20/M · 15 t/s
    46.8
    Intelligence
  22. 22G
    gemini-3-flash-preview
    ReasoningToolsJSON+246.4 intel · $0.500/M · 66 t/s
    46.4
    Intelligence
  23. 23D
    deepseek-v4-flash
    ReasoningToolsJSON46.0 intel · $0.098/M · 79 t/s
    46.0
    Intelligence
  24. 24O
    gpt-5-codex
    ReasoningToolsJSON+144.6 intel · $1.25/M · 43 t/s
    44.6
    Intelligence
  25. 25O
    gpt-5.4-nano
    ReasoningToolsJSON+144.0 intel · $0.200/M · 56 t/s
    44.0
    Intelligence

Frequently asked

What is the best LLM for reasoning?

The best LLM for reasoning is Claude Fable 5 — 64.9 intelligence with extended step-by-step thinking. Claude Opus 4.8 (61.4) and Claude Opus 4.7 (57.3) round out the top three.

What's a good alternative to Claude Fable 5?

Claude Opus 4.8 (61.4) is the closest alternative on this metric, followed by Claude Opus 4.7 (57.3). See the full ranking above for the tradeoffs.

By maker

OpenAIQwenGoogleMistralAnthropicMetaDeepSeekNVIDIA

All rankings

Small & Fast LLMsSmartest LLMsBest LLMs for CodingBest LLMs for Design & FrontendFastest LLMsLowest-Latency LLMsCheapest LLMsBest Free LLMsBest Vision LLMsBest LLMs for AgentsBest Open-Source LLMsLongest-Context LLMs