Updated July 2026

AI LLM Leaderboard - Model Rankings and TC Scores

The TC Score ranks 20 leading large language models across five weighted capability dimensions, giving you a single comparable number grounded in public benchmarks, community evaluations and our own assessments. Last recalculated July 2026.

Benchmark subjectivity notice: Rankings are necessarily subjective. Different tasks, prompt styles, and evaluation harnesses can shift results meaningfully. Always run your own evals for mission-critical use cases. Scores are approximate composites, not official vendor claims.

How the TC Score Is Calculated

The TC Score is a weighted composite of five capability dimensions. Each dimension is scored 0–100 and combined using the weights below.

Reasoning25%
Coding25%
Writing20%
Multimodal15%
Value15%

Top 3 - July 2026 Podium

2
Silver
Claude Opus 5
Anthropic
97.6
  • Best long-horizon agents
  • Adaptive effort control
  • Frontier quality at $5 per M in
1
Gold
Claude Fable 5
Anthropic
98.4
  • First public Mythos-class model
  • Best coding and writing scores
  • 1M token context window
3
Bronze
GPT-5.6 Sol
OpenAI
96.1
  • Top reasoning scores
  • Long-thinking by default
  • 1M token context

Full Rankings - All 16 Models

RankModelProviderContextCategory ScoresTC ScoreTrend
🥇Claude Fable 5Best Overall Anthropic 1M
R
99
C
99
W
98
M
95
V
88
 98.4 ⇧
🥈Claude Opus 5Best Agentic Anthropic 200K
R
98
C
98
W
96
M
94
V
97
 97.6 ⇧
🥉GPT-5.6 SolBest Reasoning OpenAI 1M
R
99
C
96
W
93
M
92
V
84
 96.1 ⇧
#4GPT-5.6Best Coding OpenAI 1M
R
95
C
97
W
94
M
93
V
94
 95.2 ⇧
#5Gemini 3.6 ProBest Context Google 2M
R
94
C
93
W
93
M
99
V
95
 94.3 ⇧
#6Claude Sonnet 5Best Value Anthropic 1M
R
93
C
95
W
94
M
91
V
98
 93.5 ⇧
#7Claude Opus 4.8 Anthropic 200K
R
94
C
94
W
93
M
91
V
93
 92.4 —
#8Gemini 3.6 FlashSpeed Pick Google 1M
R
87
C
88
W
88
M
94
V
99
 89.6 ⇧
#9Grok 4Best Live Data xAI 1M
R
89
C
90
W
88
M
86
V
88
 88.7 ⇧
#10Llama 5 BehemothBest Open Weight Meta 2M
R
90
C
88
W
86
M
89
V
94
 88.1 ⇧
#11Kimi K3.7Biggest Jump Moonshot AI 512K
R
87
C
91
W
83
M
76
V
99
 87.2 ⇧
#12GPT-5.6 Mini OpenAI 1M
R
85
C
88
W
86
M
84
V
98
 86.4 ⇧
#13DeepSeek V4.5Best Price DeepSeek 256K
R
86
C
89
W
81
M
74
V
100
 85.9 ⇧
#14Qwen 3.8Best Multilingual Alibaba 256K
R
84
C
87
W
82
M
78
V
96
 84.3 ⇧
#15Llama 5 Maverick Meta 2M
R
83
C
84
W
83
M
88
V
97
 83.6 ⇧
#16DeepSeek R2Open Reasoning DeepSeek 256K
R
92
C
84
W
76
M
68
V
99
 83.1 —
#17Claude Haiku 4.5 Anthropic 200K
R
78
C
80
W
82
M
78
V
99
 81.9 —
#18GLM-5 Zhipu AI 256K
R
82
C
85
W
79
M
72
V
97
 81.4 ⇧
#19Mistral Large 3.1Best EU Residency Mistral 256K
R
79
C
81
W
80
M
73
V
90
 79.2 —
#20Llama 5 ScoutBest Local Meta 1M
R
74
C
76
W
75
M
82
V
99
 77.6 ⇧

Category Leaders

Reasoning Leaders

1
Claude Fable 5
99
2
GPT-5.6 Sol
99
3
Claude Opus 5
98
4
GPT-5.6
95
5
Gemini 3.6 Pro
94

Coding Leaders

1
Claude Fable 5
99
2
Claude Opus 5
98
3
GPT-5.6
97
4
GPT-5.6 Sol
96
5
Claude Sonnet 5
95

Writing Leaders

1
Claude Fable 5
98
2
Claude Opus 5
96
3
GPT-5.6
94
4
Claude Sonnet 5
94
5
GPT-5.6 Sol
93

Multimodal Leaders

1
Gemini 3.6 Pro
99
2
Claude Fable 5
95
3
Claude Opus 5
94
4
Gemini 3.6 Flash
94
5
GPT-5.6
93

Speed & Value

1
DeepSeek V4.5
100
2
Gemini 3.6 Flash
99
3
Kimi K3.7
99
4
DeepSeek R2
99
5
Claude Haiku 4.5
99