Updated weekly · Last updated Oct 26, 2026
Which LLM is #1 right now?
We rank every major model on the things you actually care about — code that works, writing that sounds human, answers that are right, and what it costs you per million tokens.
#1 overallMeta
Muse Spark 1.3
Muse Spark 1.3 scores 48.1 on the Artificial Analysis Intelligence Index (highest reasoning-effort setting). List price $1.25 input / $4.25 output per 1M tokens.
- Overall score
- 83.2
- Input $/M
- $1.25
- Output $/M
- $4.25
- Context
- 1M
Find the best LLM for your task
Describe what you're building. AI picks the top 3 from this week's leaderboard.
Overall leaderboard
29 of 29 models · sort any column
| Coding | Writing | Reasoning | Speed | Cost-efficiency | Long | Multimodal | Open-source | Best | Weights | Updated | ||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Muse Spark 1.3 Meta | 83.2 | $1.25 | $4.25 | 1M | 6 | 7 | 7 | 5 | 10 | — | 6 | — | — | Closed | Oct 3, 2026 |
| 2 | Claude Sonnet 5.5 Anthropic | 81.9 | $2.00 | $10.00 | 1M | — | — | 2 | 6 | 17 | 9 | — | — | — | Closed | Oct 3, 2026 |
| 3 | Gemini 4 Argon Google DeepMind | 81.9 | $2.00 | $10.00 | 1M | — | 10 | 5 | — | 18 | 16 | — | — | — | Closed | Oct 3, 2026 |
| 4 | Claude Fable 5.1 Anthropic | 81.7 | $10.00 | $50.00 | 1M | 1 | 3 | 3 | 16 | 23 | 4 | — | — | — | Closed | Oct 3, 2026 |
| 5 | GPT-6 Astra OpenAI | 78.8 | $10.00 | $50.00 | 1M | 2 | 5 | 4 | 17 | 24 | 14 | 2 | — | — | Closed | Oct 3, 2026 |
| 6 | Claude Opus 5.5 Anthropic | 78.7 | $4.00 | $20.00 | 1M | — | 6 | 1 | 13 | 21 | 5 | 1 | — | — | Closed | Oct 3, 2026 |
| 7 | GLM-5.3 z.ai | 77.3 | $1.40 | $4.40 | 1M | 7 | 2 | 12 | 14 | 12 | 17 | — | 2 | — | Open | Oct 3, 2026 |
| 8 | Gemini 3.8 Flash Google DeepMind | 77.0 | $0.75 | $3.75 | 1M | 3 | 9 | 15 | 8 | 11 | 13 | 3 | — | — | Closed | Oct 3, 2026 |
| 9 | DeepSeek V4.1 Flash DeepSeek | 76.9 | $0.30 | $1.20 | 1M | — | 12 | 11 | 3 | 4 | 10 | 7 | 1 | — | Open | Oct 3, 2026 |
| 10 | Step 5 Preview StepFun | 76.0 | $1.00 | $2.70 | 1M | — | — | 13 | 1 | 7 | 2 | 11 | — | — | Closed | Oct 3, 2026 |
| 11 | Qwen3.8 Max Alibaba Qwen | 75.5 | $2.00 | $6.00 | 984K | 4 | — | 10 | 22 | 16 | 15 | 5 | — | — | Closed | Oct 3, 2026 |
| 12 | Kimi K3 Moonshot AI | 72.4 | $3.00 | $15.00 | 1.1M | 5 | 4 | 14 | 23 | 20 | 1 | 8 | 3 | — | Open | Oct 3, 2026 |
| 13 | MiMo-V2.6-Pro Xiaomi | 72.3 | $0.43 | $0.87 | 1M | — | — | 9 | 19 | 2 | 3 | — | — | — | Closed | Oct 3, 2026 |
| 14 | GPT-6.1 Sol OpenAI | 71.4 | $2.00 | $10.00 | 1M | — | — | 6 | 18 | 19 | 7 | 4 | — | — | Closed | Oct 3, 2026 |
| 15 | GPT-6 Luna OpenAI | 70.2 | $0.10 | $0.50 | 1M | — | — | 16 | 7 | 1 | 6 | 9 | — | — | Closed | Oct 3, 2026 |
| 16 | DeepSeek V4 Pro DeepSeek | 68.5 | $1.32 | $3.96 | 1M | 8 | 11 | 17 | 10 | 13 | — | — | 4 | — | Open | Oct 3, 2026 |
| 17 | Grok 4.7 xAI | 67.8 | $2.00 | $6.00 | 500K | — | 1 | 8 | 15 | 15 | 18 | — | — | — | Closed | Oct 3, 2026 |
| 18 | MiniMax-M3 MiniMax | 60.7 | $0.30 | $1.20 | 1M | 9 | — | 19 | 11 | 5 | 8 | 10 | 6 | — | Open | Oct 3, 2026 |
| 19 | Qwen3.8 27B Alibaba Qwen | 52.3 | $0.50 | $3.00 | 262K | — | 14 | 18 | 20 | 9 | 12 | 12 | 5 | 1 | Open | Oct 3, 2026 |
| 20 | Nemotron 3 Ultra 550B A55B NVIDIA | 47.6 | $0.60 | $2.50 | 262K | — | 8 | 21 | 2 | — | — | — | 8 | — | Open | Oct 6, 2026 |
| 21 | K2 Horizon MoVA 36B A4B Institute of Foundation Models | 43.1 | — | — | 524K | — | — | 20 | — | — | — | — | 7 | 2 | Open | Oct 3, 2026 |
| 22 | Mistral Medium 3.5 Mistral AI | 42.3 | $1.50 | $7.50 | — | 10 | — | 27 | 4 | 22 | — | — | — | — | Closed | Oct 3, 2026 |
| 23 | Gemma 4 26B A4B Google DeepMind | 41.1 | $0.10 | $0.37 | 262K | — | 13 | 24 | — | 3 | — | — | 11 | 5 | Open | Oct 3, 2026 |
| 24 | Qwen3.6 35B A3B Alibaba Qwen | 38.4 | $0.38 | $2.25 | 262K | — | — | 23 | 9 | 14 | — | — | 10 | 4 | Open | Oct 3, 2026 |
| 25 | Muse Glimmer Meta | 36.9 | $0.32 | $1.35 | 131K | — | — | 25 | 12 | 8 | — | — | 12 | 6 | Open | Oct 3, 2026 |
| 26 | K2 Horizon 7B Institute of Foundation Models | 36.2 | — | — | 524K | — | — | 22 | — | — | — | — | 9 | 3 | Open | Oct 3, 2026 |
| 27 | Granite 4.2 30B IBM | 32.3 | $0.16 | $0.65 | 131K | — | — | 26 | 21 | 6 | — | — | 13 | 7 | Open | Oct 3, 2026 |
| 28 | Claude Haiku 5.5 Anthropic | — | — | — | — | — | — | — | — | — | 11 | — | — | — | Closed | Oct 16, 2026 |
| 29 | Kolibri-1 Aleph Alpha | — | — | — | 1.0M | — | — | — | — | — | — | — | — | — | Open | Oct 6, 2026 |
1
Muse Spark 1.3
Meta
83.2
overall
- In $/M
- $1.25
- Out $/M
- $4.25
- Context
- 1M
2
Claude Sonnet 5.5
Anthropic
81.9
overall
- In $/M
- $2.00
- Out $/M
- $10.00
- Context
- 1M
3
Gemini 4 Argon
Google DeepMind
81.9
overall
- In $/M
- $2.00
- Out $/M
- $10.00
- Context
- 1M
4
Claude Fable 5.1
Anthropic
81.7
overall
- In $/M
- $10.00
- Out $/M
- $50.00
- Context
- 1M
5
GPT-6 Astra
OpenAI
78.8
overall
- In $/M
- $10.00
- Out $/M
- $50.00
- Context
- 1M
6
Claude Opus 5.5
Anthropic
78.7
overall
- In $/M
- $4.00
- Out $/M
- $20.00
- Context
- 1M
7
GLM-5.3
z.ai
77.3
overall
- In $/M
- $1.40
- Out $/M
- $4.40
- Context
- 1M
8
Gemini 3.8 Flash
Google DeepMind
77.0
overall
- In $/M
- $0.75
- Out $/M
- $3.75
- Context
- 1M
9
DeepSeek V4.1 Flash
DeepSeek
76.9
overall
- In $/M
- $0.30
- Out $/M
- $1.20
- Context
- 1M
10
Step 5 Preview
StepFun
76.0
overall
- In $/M
- $1.00
- Out $/M
- $2.70
- Context
- 1M
11
Qwen3.8 Max
Alibaba Qwen
75.5
overall
- In $/M
- $2.00
- Out $/M
- $6.00
- Context
- 984K
12
Kimi K3
Moonshot AI
72.4
overall
- In $/M
- $3.00
- Out $/M
- $15.00
- Context
- 1.1M
13
MiMo-V2.6-Pro
Xiaomi
72.3
overall
- In $/M
- $0.43
- Out $/M
- $0.87
- Context
- 1M
14
GPT-6.1 Sol
OpenAI
71.4
overall
- In $/M
- $2.00
- Out $/M
- $10.00
- Context
- 1M
15
GPT-6 Luna
OpenAI
70.2
overall
- In $/M
- $0.10
- Out $/M
- $0.50
- Context
- 1M
16
DeepSeek V4 Pro
DeepSeek
68.5
overall
- In $/M
- $1.32
- Out $/M
- $3.96
- Context
- 1M
17
Grok 4.7
xAI
67.8
overall
- In $/M
- $2.00
- Out $/M
- $6.00
- Context
- 500K
18
MiniMax-M3
MiniMax
60.7
overall
- In $/M
- $0.30
- Out $/M
- $1.20
- Context
- 1M
19
Qwen3.8 27B
Alibaba Qwen
52.3
overall
- In $/M
- $0.50
- Out $/M
- $3.00
- Context
- 262K
20
Nemotron 3 Ultra 550B A55B
NVIDIA
47.6
overall
- In $/M
- $0.60
- Out $/M
- $2.50
- Context
- 262K
21
K2 Horizon MoVA 36B A4B
Institute of Foundation Models
43.1
overall
- In $/M
- —
- Out $/M
- —
- Context
- 524K
22
Mistral Medium 3.5
Mistral AI
42.3
overall
- In $/M
- $1.50
- Out $/M
- $7.50
- Context
- —
23
Gemma 4 26B A4B
Google DeepMind
41.1
overall
- In $/M
- $0.10
- Out $/M
- $0.37
- Context
- 262K
24
Qwen3.6 35B A3B
Alibaba Qwen
38.4
overall
- In $/M
- $0.38
- Out $/M
- $2.25
- Context
- 262K
25
Muse Glimmer
Meta
36.9
overall
- In $/M
- $0.32
- Out $/M
- $1.35
- Context
- 131K
26
K2 Horizon 7B
Institute of Foundation Models
36.2
overall
- In $/M
- —
- Out $/M
- —
- Context
- 524K
27
Granite 4.2 30B
IBM
32.3
overall
- In $/M
- $0.16
- Out $/M
- $0.65
- Context
- 131K
28
Claude Haiku 5.5
Anthropic
—
overall
- In $/M
- —
- Out $/M
- —
- Context
- —
29
Kolibri-1
Aleph Alpha
—
overall
- In $/M
- —
- Out $/M
- —
- Context
- 1.0M
Best for Coding
Claude Fable 5.1
Claude Fable 5.1 has the highest Artificial Analysis Coding Index of the models we track — an independent test of writing and fixing real code.
Best for Writing
Grok 4.7
Grok 4.7 currently ranks #1 in this category across the benchmarks and pricing data we track.
Best for Reasoning & Math
Claude Opus 5.5
Claude Opus 5.5 has the highest Artificial Analysis Intelligence Index of the models we track, which combines ten hard tests of maths, science, coding and reasoning.
Best for Speed
Step 5 Preview
Step 5 Preview produces answers faster than any other model we track, based on Artificial Analysis's measured median output speed.