Best LLM
What is the best LLM for general tasks?
Claude Fable 5.2 leads in general tasks.
Among the ten best, Claude Sonnet 5.5 is the cheapest at $4 per million tokens.
The fastest among them is Claude Sonnet 5.5, at 103 tokens per second.
- Ranked models
- 69
- Tests
- 7
- Data as of
- Nov 10, 2026
Ranking: General tasks
Place and value in the area, plus overall index, price and speed. Higher values are better.
| Rank | Model | Value | Overall index | Price (3:1) | Speed |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2Top group | 132.8 | 130.9 | $16 | n/a |
| 2 | GPT-6 AstraUpper group | 126.7 | 120.2 | $20 | 58 |
| 3 | Claude Opus 5.5Upper group | 125.2 | 125.6 | $8 | 75 |
| 4 | Claude Sonnet 5.5Upper group | 124.5 | 121.8 | $4 | 103 |
| 5 | Claude Fable 5.1Upper group | 122.8 | 124.1 | $20 | 59 |
| 6 | GPT-6.1 SolUpper group | 122.4 | 118.0 | $4 | 44 |
| 7 | Gemini 4 ArgonUpper group | 121.4 | 121.4 | $4 | 46 |
| 8 | Claude Opus 5Upper group | 116.4 | 117.4 | $10 | 71 |
| 9 | Muse Wonder FullMiddle group | 113.7 | 118.1 | n/a | n/a |
| 10 | GPT-6 SolMiddle group | 113.3 | 109.1 | $4 | 82 |
| 11 | Kimi K3.1 ProMiddle group | 111.6 | 112.6 | $4 | 56 |
| 12 | GPT-5.6 SolMiddle group | 111.5 | 109.1 | $8 | 75 |
| 13 | Muse Spark 1.3Middle group | 108.3 | 107.3 | $2 | 102 |
| 14 | DeepSeek V4.1 Flash 1017Middle group | 107.0 | 106.7 | $0.26 | 126 |
| 15 | Claude Haiku 5.5Middle group | 106.2 | 102.8 | $0.20 | 164 |
| 16 | Muse WonderMiddle group | 106.0 | 113.3 | $8 | n/a |
| 17 | Grok 4.6Middle group | 105.8 | 102.1 | $3 | 58 |
| 18 | Gemini 3.8 FlashMiddle group | 105.2 | 106.8 | $1.50 | 81 |
| 19 | MiniMax M3.1 FlashMiddle group | 104.9 | 100.0 | $0.26 | n/a |
| 20 | GPT-5.6 TerraMiddle group | 104.4 | 100.8 | $4.50 | 72 |
Show all 69 ranked models
| Rank | Model | Value | Overall index | Price (3:1) | Speed |
|---|---|---|---|---|---|
| 21 | Gemini 3.7 FlashMiddle group | 104.3 | 107.9 | n/a | 72 |
| 22 | GLM-5.3Middle group | 103.3 | 100.6 | $2.15 | 81 |
| 23 | Qwen 3.8 Max 0902Middle group | 102.9 | 100.8 | $2.48 | 36 |
| 24 | Kimi K3Middle group | 102.7 | 101.1 | $6 | 61 |
| 25 | Grok 4.7Middle group | 102.2 | 103.3 | $3 | 47 |
| 26 | Claude Fable 5Middle group | 102.0 | 112.8 | $20 | 50 |
| 27 | Inkling 2 SmallMiddle group | 101.5 | n/a | n/a | n/a |
| 28 | Hy4 previewMiddle group | 101.2 | n/a | n/a | n/a |
| 29 | GPT-5.5Middle group | 100.8 | 101.5 | $11.25 | 87 |
| 30 | MiMo V2.6 FlashMiddle group | 99.7 | 97.3 | $0.18 | 38 |
| 31 | Ember-1Middle group | 99.6 | n/a | n/a | n/a |
| 32 | DeepSeek-V4.1-FlashMiddle group | 96.9 | 99.5 | $0.26 | 118 |
| 33 | Gemini 3.5 FlashMiddle group | 96.3 | 97.8 | n/a | 142 |
| 34 | GPT-6 LunaMiddle group | 94.6 | 95.8 | $0.20 | 77 |
| 35 | Step 5 PreviewMiddle group | 93.6 | 97.1 | $1.43 | 65 |
| 36 | MiMo V2.6 ProMiddle group | 92.5 | 100.4 | $0.54 | 32 |
| 37 | Gemini 3.6 FlashMiddle group | 91.8 | 97.6 | $1.50 | 110 |
| 38 | Gemini 3.1 Pro PreviewMiddle group | 91.3 | 91.4 | $4.50 | 96 |
| 39 | Grok 4.5Middle group | 90.7 | 94.8 | $3 | 52 |
| 40 | GLM-5.3-FlashMiddle group | 90.7 | 94.3 | $0.24 | 101 |
| 41 | GPT-5.6 LunaMiddle group | 89.5 | 93.8 | $0.45 | 123 |
| 42 | Claude Sonnet 5Middle group | 87.6 | 92.1 | $4 | 77 |
| 43 | GLM-5.2Middle group | 87.4 | 89.0 | $2.15 | 73 |
| 44 | MiniMax M3Middle group | 85.6 | 83.0 | $0.52 | 82 |
| 45 | Reflection BeamLower group | 81.5 | 82.4 | n/a | n/a |
| 46 | InklingLower group | 81.0 | 72.1 | $1.76 | n/a |
| 47 | Claude Sonnet 4.6Lower group | 80.7 | 86.7 | $6 | 38 |
| 48 | Grok 4.3Lower group | 80.5 | 71.6 | $1.56 | 66 |
| 49 | GPT-5.4 miniLower group | 79.4 | 75.1 | $1.69 | 134 |
| 50 | GPT-5Lower group | 78.1 | 77.5 | $3.44 | 83 |
| 51 | Gemini 3.5 Flash-LiteLower group | 73.5 | 73.7 | $0.85 | 145 |
| 52 | Nemotron 3 UltraLower group | 73.2 | 66.8 | $0.93 | 92 |
| 53 | MiMo-V2.5Lower group | 70.9 | 69.1 | $0.18 | 55 |
| 54 | MiniMax M2.7Lower group | 70.5 | 65.1 | $0.37 | 45 |
| 55 | GPT-5.4 nanoLower group | 69.0 | 64.0 | $0.46 | 98 |
| 56 | GPT-5 miniLower group | 67.5 | 65.8 | $0.69 | 105 |
| 57 | Inkling SmallLower group | 66.9 | 68.7 | $0.52 | 61 |
| 58 | Gemini 3.1 Flash-LiteLower group | 66.8 | 55.9 | $0.56 | 125 |
| 59 | MiniMax M2.5Lower group | 63.2 | 61.5 | $0.52 | 49 |
| 60 | Gemini 2.5 ProLower group | 58.9 | 61.4 | $3.44 | 74 |
| 61 | Mistral Medium 3.5Lower group | 54.7 | 46.3 | $3 | 118 |
| 62 | Command A PlusLower group | 48.6 | 30.7 | n/a | n/a |
| 63 | GLM-4.5Lower group | 45.5 | 48.8 | $1 | 28 |
| 64 | GPT OSS 120BLower group | 43.9 | 43.4 | $0.20 | 92 |
| 65 | North Mini CodeLower group | 41.0 | n/a | n/a | n/a |
| 66 | GPT-5 nanoLower group | 38.4 | 32.4 | $0.14 | 136 |
| 67 | Mistral Large 3Lower group | 33.6 | 32.7 | $0.75 | 86 |
| 68 | GPT OSS 20BLower group | 32.5 | 30.9 | $0.06 | 85 |
| 69 | DeepSeek-V3Lower group | 17.5 | 19.7 | $0.37 | 40 |
Price in dollars per million tokens, mixed from 3 parts input and 1 part output. Speed in tokens per second.
Claude Fable 5.2Rank 1132.8
GPT-6 AstraRank 2126.7
Claude Opus 5.5Rank 3125.2
Claude Sonnet 5.5Rank 4124.5
Claude Fable 5.1Rank 5122.8
GPT-6.1 SolRank 6122.4
Gemini 4 ArgonRank 7121.4
Claude Opus 5Rank 8116.4
Muse Wonder FullRank 9113.7
GPT-6 SolRank 10113.3
Kimi K3.1 ProRank 11111.6
GPT-5.6 SolRank 12111.5
Muse Spark 1.3Rank 13108.3
DeepSeek V4.1 Flash 1017Rank 14107.0
Claude Haiku 5.5Rank 15106.2
Muse WonderRank 16106.0
Grok 4.6Rank 17105.8
Gemini 3.8 FlashRank 18105.2
MiniMax M3.1 FlashRank 19104.9
GPT-5.6 TerraRank 20104.4
Which tests count here?
7 tests by independent evaluators feed this area. Each test counts with the result of the model in question.
IFBench
124 models tested · Artificial Analysis
LMArena Text, Style Control
80 models tested · LMArena
HLE-Diamond
57 models tested · Artificial Analysis
SRE Bench
34 models tested · Vals AI
BioMysteryBench
29 models tested · Vals AI
MysteryMechanism
29 models tested · Vals AI
Access to Justice
22 models tested · Vals AI
Popular comparisons among the best
Other tasks
All LLMs comparedHow the overall index worksCompare several models