Capability ranking
Best AI for Reasoning
Best Reasoning Models
Updated 2026-08-11
Ranked models227
Vendors24
Open-weight models50
Official prices101
What this ranking says
A quick reading of the current reasoning ranking before the full data table.
Claude Opus 5 leads this page at 100.0, 0.2 points ahead of Claude Mythos.
Kimi K3 is the highest-ranked open-weight option at #7. Nova Micro has the lowest official input price among ranked models.
Reasoning Ranking Leaders
The leading reasoning scores, with the axis focused on the competitive range rather than zero.
Reasoning Capability Profile
Compare reasoning strength with each model's broader capability score.
ModelReasoningKnowledgeMathCodingInstruction
Reasoning scoreOverall score
80 models with comparable dataOpen a model by selecting its logo
Reasoning Model Ranking
Models are ordered by their reasoning score.
| 1 | AN | Claude Opus 5 | 100.0 | 97.4 | 75.0 | 99.5 | 90.4 | N/A | 80.0% | 1M | Closed weights | $5 | $25 |
| 2 | AN | Claude Mythos Preview | 99.8 | 93.6 | 100.0 | 99.7 | 92.7 | 93.3 | 100.0% | N/A | Closed weights | N/A | N/A |
| 3 | AN | Claude Opus 4.8 | 99.0 | 87.9 | 37.5 | 94.6 | 85.0 | 84.7 | 100.0% | 1M | Closed weights | $5 | $25 |
| 4 | OP | GPT-5.5 | 98.8 | 84.0 | 100.0 | 73.1 | 73.8 | 72.2 | 100.0% | 1.1M | Closed weights | $5 | $30 |
| 5 | AN | Claude Opus 4.7 | 98.7 | 84.2 | N/A | 88.6 | 69.3 | 89.5 | 80.0% | 1M | Closed weights | $5 | $25 |
| 6 | AC | Qwen3.8 Max | 97.8 | 89.3 | N/A | 70.7 | 85.8 | 97.9 | 80.0% | 1M | Closed weights | $2 | $6 |
| 7 | MA | Kimi K3 | 97.0 | 93.0 | 50.0 | 95.7 | 94.1 | 97.9 | 100.0% | 1M | Open weights | $3 | $15 |
| 8 | AC | Qwen3.7 Max | 95.7 | 78.8 | N/A | 77.4 | 83.1 | 89.6 | 80.0% | 1M | Closed weights | $2.5 | $7.5 |
| 9 | ZA | GLM-5.2 | 92.7 | 79.3 | N/A | 89.5 | 56.5 | 100.0 | 80.0% | 1M | Open weights | $1.4 | $4.4 |
| 10 | GO | Gemini 3.1 Pro | 91.8 | 77.5 | N/A | 82.6 | 55.9 | 74.1 | 80.0% | 1M | Closed weights | $2 | $12 |
| 11 | AC | Qwen3.5-397B-A17B | 90.8 | 66.3 | N/A | 53.7 | 69.8 | 80.0 | 80.0% | 262.1K | Open weights | $0.60 | $3.6 |
| 12 | OP | GPT-5.4 | 90.3 | 77.1 | 83.3 | 72.2 | 57.8 | 71.2 | 100.0% | 1.1M | Closed weights | $2.5 | $15 |
| 13 | DE | DeepSeek-V4-Pro-Max | 90.1 | 73.8 | N/A | 86.0 | 63.2 | 85.4 | 80.0% | 1M | Closed weights | $0.435 | $0.87 |
| 14 | GO | Gemini 3.5 Flash | 90.0 | 79.2 | N/A | 65.2 | 64.5 | 60.5 | 80.0% | 1M | Closed weights | $1.5 | $9 |
| 15 | BY | Seed 2.0 Pro | 88.8 | 69.5 | N/A | N/A | 75.9 | 89.4 | 60.0% | 256K | Closed weights | N/A | N/A |
| 16 | XA | Grok-4 Heavy | 88.2 | 68.2 | N/A | 76.8 | 86.1 | 98.2 | 80.0% | N/A | Closed weights | N/A | N/A |
| 17 | OP | GPT-5.6 Sol | 87.8 | 95.1 | 95.8 | 100.0 | 92.9 | 90.6 | 100.0% | 1.1M | Closed weights | $5 | $30 |
| 18 | ME | Muse Spark 1.1 | 87.5 | 88.3 | N/A | 96.7 | 75.7 | 89.4 | 80.0% | 1M | Closed weights | $1.25 | $4.25 |
| 19 | OP | GPT-5.1 | 86.5 | 62.1 | 96.8 | 50.0 | 70.9 | 77.9 | 100.0% | 400K | Closed weights | $1.25 | $10 |
| 20 | OP | GPT-5.1 Instant | 86.5 | 61.3 | 96.8 | 50.0 | 70.9 | 77.9 | 100.0% | 400K | Closed weights | N/A | N/A |
| 21 | AC | Qwen3.6 Plus | 84.9 | 67.5 | 82.0 | 74.4 | 48.8 | 77.3 | 100.0% | 1M | Closed weights | $0.50 | $3 |
| 22 | MA | Mistral NeMo Instruct | 83.3 | 0.0 | 33.1 | N/A | N/A | 26.5 | 60.0% | 128K | Closed weights | $0.15 | $0.15 |
| 23 | NV | Nemotron 3 Ultra (550B A55B) | 82.6 | 62.9 | N/A | 53.6 | 46.0 | 89.9 | 80.0% | 1M | Open weights | $0.50 | $2.5 |
| 24 | MA | Pixtral Large | 82.1 | 21.2 | 38.7 | 63.2 | N/A | 65.6 | 80.0% | 128K | Closed weights | N/A | N/A |
| 25 | GO | Gemini 2.5 Pro Preview 06-05 | 81.1 | 49.9 | 70.7 | 39.1 | 66.1 | 72.6 | 100.0% | 1M | Closed weights | $1.25 | $10 |
| 26 | ZA | GLM-5.1 | 80.7 | 69.6 | N/A | 68.0 | 47.1 | 54.8 | 80.0% | 200K | Open weights | $1.4 | $4.4 |
| 27 | AN | Claude 3.5 Sonnet | 80.4 | 32.1 | 45.2 | 76.1 | 48.8 | 80.4 | 100.0% | 200K | Closed weights | N/A | N/A |
| 28 | BY | Seed 2.1 Pro | 80.1 | 78.7 | 91.7 | 58.8 | 64.3 | 93.1 | 100.0% | N/A | Closed weights | N/A | N/A |
| 29 | AC | Qwen3.6-27B | 79.4 | 60.5 | 83.8 | 54.8 | 45.5 | 72.7 | 100.0% | 262.1K | Open weights | $0.60 | $3.6 |
| 30 | ZA | GLM-4.7 | 79.4 | 59.7 | N/A | 53.7 | 47.9 | 81.4 | 80.0% | 204.8K | Open weights | $0.60 | $2.2 |
| 31 | XA | Grok 4 Fast | 79.4 | 54.0 | N/A | 50.5 | 53.2 | 82.1 | 80.0% | 2M | Closed weights | N/A | N/A |
| 32 | ME | Muse Spark | 78.9 | 73.2 | 100.0 | 95.7 | 49.4 | 89.8 | 100.0% | N/A | Closed weights | N/A | N/A |
| 33 | OP | GPT-5.2 Pro | 78.5 | 71.6 | 66.7 | 79.9 | 63.2 | 98.2 | 100.0% | 400K | Closed weights | $21 | $168 |
| 34 | MA | Kimi K2.6 | 78.5 | 75.5 | N/A | 69.0 | 70.5 | 71.5 | 80.0% | 262.1K | Open weights | $0.95 | $4 |
| 35 | BY | Seed 2.0 Lite | 77.7 | 53.6 | N/A | N/A | 65.6 | 72.6 | 60.0% | N/A | Closed weights | N/A | N/A |
| 36 | AN | Claude Opus 4.6 | 77.5 | 79.6 | 50.0 | 85.9 | 72.2 | 77.2 | 100.0% | 1M | Closed weights | $5 | $25 |
| 37 | BA | ERNIE 5.0 | 77.3 | 58.7 | N/A | 62.0 | N/A | 78.8 | 60.0% | N/A | Closed weights | N/A | N/A |
| 38 | AN | Claude 3.7 Sonnet | 76.8 | 38.7 | 66.1 | 56.5 | 60.5 | 51.3 | 100.0% | 200K | Closed weights | N/A | N/A |
| 39 | XA | Grok-3 | 76.2 | 54.8 | 74.2 | N/A | 86.1 | 75.2 | 80.0% | 128K | Closed weights | N/A | N/A |
| 40 | MI | MAI-Code-1-Flash | 76.2 | 50.4 | N/A | 20.0 | 31.1 | 55.7 | 80.0% | 256K | Closed weights | N/A | N/A |
| 41 | MA | Kimi K2-Thinking-0905 | 75.5 | 61.0 | N/A | 60.2 | 55.0 | 67.0 | 80.0% | 262.1K | Closed weights | $0.60 | $2.5 |
| 42 | OP | GPT-5.2 | 75.5 | 71.4 | 60.7 | 76.1 | 59.1 | 85.6 | 100.0% | 400K | Closed weights | $1.75 | $14 |
| 43 | MI | MAI-Thinking-1 | 74.5 | 55.1 | 13.6 | 30.0 | 54.4 | 75.1 | 100.0% | N/A | Closed weights | N/A | N/A |
| 44 | XA | Grok-3 Mini | 73.6 | 48.4 | N/A | N/A | 90.3 | 61.1 | 60.0% | 128K | Closed weights | N/A | N/A |
| 45 | XI | MiMo-V2-Flash | 73.0 | 51.3 | N/A | 38.4 | 44.9 | 60.0 | 80.0% | 262.1K | Open weights | $0.14 | $0.28 |
| 46 | OP | GPT-5.4 mini | 72.5 | 60.5 | N/A | 51.1 | 37.7 | 54.4 | 80.0% | 400K | Closed weights | $0.75 | $4.5 |
| 47 | AC | Qwen3.7-Plus | 72.1 | 73.8 | 92.0 | 62.4 | 59.0 | 90.1 | 100.0% | 1M | Closed weights | $0.50 | $3 |
| 48 | AN | Claude Sonnet 4.5 | 72.1 | 56.0 | 33.3 | N/A | 90.8 | 62.9 | 80.0% | 200K | Closed weights | $3 | $15 |
| 49 | GO | Gemini 3.1 Flash-Lite | 71.8 | 51.9 | 80.0 | 27.2 | 10.3 | 50.1 | 100.0% | 1M | Closed weights | $0.25 | $1.5 |
| 50 | AC | Qwen3-235B-A22B-Thinking-2507 | 71.4 | 48.5 | N/A | 46.6 | 40.4 | 80.0 | 80.0% | 262.1K | Closed weights | N/A | N/A |
| 51 | OP | GPT-5.6 Terra | 71.4 | 87.6 | 50.0 | 71.9 | 79.1 | 66.0 | 100.0% | 1.1M | Closed weights | $2 | $12 |
| 52 | AM Nova 2 ProAmazon | Nova 2 Pro | 71.4 | 52.5 | N/A | N/A | 57.3 | 70.2 | 60.0% | N/A | Closed weights | N/A | N/A |
| 53 | GO | Gemini 3 Flash | 71.1 | 64.8 | 96.0 | 69.6 | 46.1 | 57.9 | 100.0% | 1M | Closed weights | $0.50 | $3 |
| 54 | GO | Gemini 2.5 Flash | 70.6 | 38.1 | 79.0 | 14.1 | 46.1 | 52.5 | 100.0% | 1M | Closed weights | $0.30 | $2.5 |
| 55 | AN | Claude Sonnet 4.6 | 70.1 | 72.6 | N/A | 78.3 | 62.2 | 72.3 | 80.0% | 1M | Closed weights | $3 | $15 |
| 56 | XI | MiMo-V2.5-Pro | 70.0 | 46.7 | 88.2 | 82.7 | 50.1 | 72.7 | 100.0% | 1M | Open weights | $0.435 | $0.87 |
| 57 | NV | Nemotron 3 Super (120B A12B) | 70.0 | 44.8 | N/A | 60.8 | 23.5 | 64.5 | 80.0% | 262.1K | Open weights | $0.20 | $0.80 |
| 58 | GO | Gemma 4 31B | 69.5 | 60.1 | 63.6 | 62.1 | 71.7 | 76.0 | 100.0% | 262.1K | Open weights | N/A | N/A |
| 59 | GO | Gemma 2 27B | 69.3 | 0.1 | 97.1 | 25.6 | 8.6 | 64.2 | 100.0% | N/A | Closed weights | N/A | N/A |
| 60 | MI | MiniMax M3 | 69.2 | 71.3 | 74.0 | 100.0 | 53.8 | 62.6 | 100.0% | 512K | Open weights | $0.30 | $1.2 |
| 61 | MA | Kimi K2.5 | 69.0 | 66.0 | 46.0 | 73.6 | 48.1 | 60.3 | 100.0% | 262.1K | Open weights | $0.60 | $3 |
| 62 | GO | Gemini 3 Pro | 68.8 | 67.3 | 100.0 | 36.4 | 60.5 | 64.3 | 100.0% | 1M | Closed weights | N/A | N/A |
| 63 | OP | GPT-5 mini | 68.5 | 44.9 | N/A | 33.4 | N/A | 63.3 | 60.0% | 400K | Closed weights | $0.25 | $2 |
| 64 | OP | GPT-5.5 Instant | 67.7 | 53.7 | 6.3 | N/A | N/A | 38.4 | 60.0% | 400K | Closed weights | N/A | N/A |
| 65 | OP | o4-mini | 66.7 | 45.0 | 82.3 | 57.2 | 52.2 | 44.5 | 100.0% | 200K | Closed weights | $1.1 | $4.4 |
| 66 | AC | Qwen3 VL 32B Thinking | 65.5 | 40.5 | 64.8 | 60.6 | 60.2 | 58.1 | 100.0% | N/A | Closed weights | N/A | N/A |
| 67 | AC | Qwen3 VL 235B A22B Instruct | 65.5 | 43.2 | 45.3 | 44.6 | 59.3 | 62.5 | 100.0% | 262.1K | Closed weights | N/A | N/A |
| 68 | AMNova ProAmazon | Nova Pro | 65.3 | 20.9 | 66.1 | 80.7 | 52.7 | 75.0 | 100.0% | 300K | Closed weights | $0.80 | $3.2 |
| 69 | ZA | GLM-4.6 | 65.2 | 54.2 | N/A | 29.9 | 50.4 | 76.1 | 80.0% | 204.8K | Open weights | $0.60 | $2.2 |
| 70 | MI | MiniMax M2.1 | 65.2 | 53.7 | N/A | 40.8 | 51.5 | 58.9 | 80.0% | 204.8K | Open weights | $0.30 | $1.2 |
| 71 | DE | DeepSeek-R1-0528 | 65.2 | 44.2 | N/A | 28.3 | 22.5 | 77.2 | 80.0% | 131.1K | Closed weights | N/A | N/A |
| 72 | AN | Claude Opus 4.1 | 64.2 | 52.4 | 66.7 | N/A | 75.8 | 57.4 | 80.0% | 200K | Closed weights | N/A | N/A |
| 73 | OP | GPT OSS 120B High | 64.2 | 44.0 | N/A | N/A | 47.9 | 55.9 | 60.0% | 131.1K | Closed weights | N/A | N/A |
| 74 | ME | LongCat-Flash-Thinking-2601 | 63.5 | 60.8 | N/A | 28.6 | 76.2 | 93.4 | 80.0% | 128K | Closed weights | N/A | N/A |
| 75 | AC | Qwen3.5-122B-A10B | 61.7 | 59.2 | 87.8 | 73.4 | 51.6 | 68.5 | 100.0% | 262.1K | Open weights | $0.40 | $3.2 |
| 76 | ZA | GLM-4.5 | 61.4 | 49.3 | N/A | 56.8 | 58.4 | 84.5 | 80.0% | 131.1K | Open weights | $0.60 | $2.2 |
| 77 | AN | Claude Opus 4.5 | 61.3 | 69.5 | 100.0 | N/A | 71.1 | 78.9 | 80.0% | 200K | Closed weights | $5 | $25 |
| 78 | ME | Llama 3.1 405B Instruct | 61.1 | 24.5 | N/A | 76.5 | 87.7 | 68.0 | 80.0% | 128K | Closed weights | N/A | N/A |
| 79 | AC | Qwen3-235B-A22B-Instruct-2507 | 61.1 | 42.4 | 0.0 | 20.8 | 40.2 | 65.8 | 100.0% | 262.1K | Open weights | $0.70 | $2.8 |
| 80 | MI | Phi-3.5-MoE-instruct | 60.9 | 4.9 | 100.0 | 34.3 | 39.7 | 57.6 | 100.0% | N/A | Closed weights | N/A | N/A |
| 81 | ME | Muse Glimmer-30B | 60.1 | 58.5 | N/A | 40.8 | 45.3 | 62.9 | 80.0% | 131.1K | Open weights | N/A | N/A |
| 82 | SA | Sarvam-105B | 60.1 | 44.6 | N/A | 49.9 | 28.8 | 65.1 | 80.0% | 131.1K | Open weights | N/A | N/A |
| 83 | MI | MiniMax M2 | 59.4 | 43.9 | N/A | 17.4 | 41.4 | 52.4 | 80.0% | 196.6K | Open weights | $0.30 | $1.2 |
| 84 | OP | o1 | 59.4 | 36.3 | 72.6 | 66.3 | 46.7 | 56.3 | 100.0% | 200K | Closed weights | $15 | $60 |
| 85 | AC | Qwen3.5-27B | 59.4 | 57.2 | 68.6 | 78.5 | 44.5 | 69.3 | 100.0% | 262.1K | Open weights | $0.30 | $2.4 |
| 86 | AN | Claude 3 Opus | 59.2 | 16.7 | N/A | 60.5 | 46.1 | 72.7 | 80.0% | 200K | Closed weights | N/A | N/A |
| 87 | AC | Qwen3.5-9B | 58.9 | 41.4 | N/A | 28.1 | 33.5 | 46.6 | 80.0% | 262.1K | Open weights | N/A | N/A |
| 88 | AC | Qwen3 VL 32B Instruct | 58.8 | 35.2 | 70.6 | 48.9 | 46.4 | 43.9 | 100.0% | N/A | Closed weights | N/A | N/A |
| 89 | AC | Qwen3-Next-80B-A3B-Thinking | 58.2 | 40.9 | N/A | 37.5 | 41.2 | 64.5 | 80.0% | 131.1K | Open weights | $0.50 | $6 |
| 90 | OP | o3-mini | 58.1 | 36.3 | N/A | 56.3 | 36.2 | 63.9 | 80.0% | 200K | Closed weights | $1.1 | $4.4 |
| 91 | MA | Mistral Small 3.2 24B Instruct | 57.7 | 15.9 | 35.5 | 45.8 | N/A | 36.4 | 80.0% | N/A | Closed weights | N/A | N/A |
| 92 | GO | Gemma 4 26B-A4B | 57.3 | 52.6 | 54.5 | 47.2 | 67.5 | 63.8 | 100.0% | 262.1K | Open weights | N/A | N/A |
| 93 | AC | Qwen2-VL-72B-Instruct | 57.1 | 25.5 | 34.4 | 18.2 | N/A | 81.3 | 80.0% | N/A | Closed weights | N/A | N/A |
| 94 | NV | Llama 3.1 Nemotron Ultra 253B v1 | 57.1 | 30.5 | N/A | 75.8 | 66.7 | 48.1 | 80.0% | N/A | Closed weights | N/A | N/A |
| 95 | AC | Qwen3.6-35B-A3B | 57.0 | 55.3 | 74.0 | 47.4 | 26.5 | 72.1 | 100.0% | 262.1K | Open weights | $0.248 | $1.49 |
| 96 | ME | Llama 4 Scout | 56.3 | 14.1 | 46.8 | 44.3 | 23.8 | 60.0 | 100.0% | 10M | Closed weights | N/A | N/A |
| 97 | AN | Claude Sonnet 4 | 56.2 | 39.5 | 62.9 | N/A | 65.9 | 38.6 | 80.0% | 200K | Closed weights | N/A | N/A |
| 98 | ZA | GLM-4.7-Flash | 55.8 | 38.5 | N/A | 20.1 | 17.7 | 64.6 | 80.0% | 200K | Open weights | N/A | N/A |
| 99 | OP | GPT-5.6 Luna | 55.2 | 76.4 | 25.0 | 43.8 | 68.6 | 40.8 | 100.0% | 1.1M | Closed weights | $0.20 | $1.2 |
| 100 | MA | Kimi K2-Instruct-0905 | 55.1 | 37.2 | N/A | 42.5 | 31.7 | 50.0 | 80.0% | N/A | Closed weights | $0.60 | $2.5 |
| 101 | OP | GPT-5.4 nano | 54.5 | 49.1 | N/A | 45.6 | 19.8 | 35.6 | 80.0% | 400K | Closed weights | $0.20 | $1.25 |
| 102 | ZA | GLM-4.5-Air | 54.3 | 41.5 | N/A | 51.1 | 48.2 | 74.9 | 80.0% | 131.1K | Open weights | $0.20 | $1.1 |
| 103 | NV | Nemotron 3 Nano (30B A3B) | 54.3 | 35.2 | N/A | 25.0 | 9.7 | 65.2 | 80.0% | 262.1K | Open weights | N/A | N/A |
| 104 | AC | Qwen3 VL 235B A22B Thinking | 53.9 | 45.8 | 45.3 | 48.7 | 61.6 | 62.2 | 100.0% | 262.1K | Closed weights | N/A | N/A |
| 105 | ME | Llama 4 Maverick | 53.8 | 24.9 | 61.3 | 58.6 | 43.2 | 79.5 | 100.0% | 1M | Closed weights | N/A | N/A |
| 106 | DE | DeepSeek-V3.1 | 53.6 | 39.9 | N/A | 14.6 | 31.4 | 61.6 | 80.0% | 131.1K | Open weights | N/A | N/A |
| 107 | AC | Qwen3-Next-80B-A3B-Instruct | 53.4 | 36.6 | N/A | 16.7 | 28.4 | 54.1 | 80.0% | 131.1K | Open weights | $0.50 | $2 |
| 108 | BY | Seed 2.1 Turbo | 52.6 | 73.1 | 41.7 | 66.6 | 53.5 | 87.5 | 100.0% | N/A | Closed weights | N/A | N/A |
| 109 | GO | Gemini 2.0 Flash Thinking | 52.6 | 29.9 | 71.0 | N/A | N/A | 30.8 | 60.0% | N/A | Closed weights | N/A | N/A |
| 110 | XA | Grok-4 | 51.9 | 56.5 | N/A | 47.8 | 83.3 | 65.5 | 80.0% | 256K | Closed weights | N/A | N/A |
| 111 | GO | Gemma 4 12B | 51.8 | 38.2 | 36.4 | 32.8 | 29.3 | 41.9 | 100.0% | N/A | Closed weights | N/A | N/A |
| 112 | ME | Llama 3.1 70B Instruct | 51.8 | 13.2 | N/A | 77.6 | 61.2 | 41.9 | 80.0% | 128K | Closed weights | N/A | N/A |
| 113 | IN | Mercury 2 | 51.7 | 39.3 | N/A | N/A | 35.2 | 56.6 | 60.0% | 128K | Closed weights | $0.25 | $0.75 |
| 114 | AMNova LiteAmazon | Nova Lite | 51.1 | 13.2 | 35.5 | 59.9 | 34.2 | 42.6 | 100.0% | 300K | Closed weights | $0.06 | $0.24 |
| 115 | MI | Phi-3.5-mini-instruct | 50.7 | 0.0 | 62.5 | 24.4 | 18.7 | 31.5 | 100.0% | 128K | Closed weights | N/A | N/A |
| 116 | ME | LongCat-Flash-Chat | 50.2 | 36.9 | N/A | 54.8 | 42.8 | 55.5 | 80.0% | 128K | Closed weights | N/A | N/A |
| 117 | OP | o3 | 50.1 | 52.6 | 63.8 | 47.3 | 51.0 | 62.1 | 100.0% | 200K | Closed weights | $2 | $8 |
| 118 | AN | Claude Haiku 4.5 | 48.9 | 45.5 | 0.0 | N/A | 55.1 | 33.0 | 80.0% | 200K | Closed weights | $1 | $5 |
| 119 | AN | Claude 3 Sonnet | 48.8 | 3.5 | N/A | 38.7 | 20.0 | 53.6 | 80.0% | 200K | Closed weights | N/A | N/A |
| 120 | MA | Ministral 8B Instruct | 48.5 | 0.0 | 17.6 | 19.1 | 0.0 | 26.1 | 100.0% | 131.1K | Open weights | N/A | N/A |
| 121 | GO | Gemma 2 9B | 48.0 | 0.0 | 72.3 | 18.4 | 2.3 | 41.3 | 100.0% | N/A | Closed weights | N/A | N/A |
| 122 | OP | GPT-5 nano | 47.2 | 31.1 | N/A | 16.8 | N/A | 47.8 | 60.0% | 400K | Closed weights | $0.05 | $0.40 |
| 123 | MA | Magistral Medium | 46.4 | 19.8 | N/A | 10.9 | 29.7 | 18.6 | 80.0% | N/A | Closed weights | N/A | N/A |
| 124 | AL | Jamba 1.5 Large | 46.1 | 2.7 | N/A | 31.9 | N/A | 27.4 | 60.0% | 256K | Closed weights | N/A | N/A |
| 125 | TE | Hy3 | 45.7 | 71.0 | 0.0 | 47.2 | 63.0 | N/A | 80.0% | 256K | Open weights | N/A | N/A |
| 126 | AC | Qwen3 VL 30B A3B Thinking | 45.6 | 31.8 | 52.3 | 43.3 | 38.8 | 39.6 | 100.0% | 262.1K | Closed weights | N/A | N/A |
| 127 | AC | Qwen3.5-4B | 45.4 | 32.4 | N/A | 18.8 | 20.6 | 35.5 | 80.0% | N/A | Closed weights | N/A | N/A |
| 128 | MI | MiniMax M1 80K | 45.1 | 37.0 | N/A | 39.0 | 56.9 | 46.3 | 80.0% | 1M | Closed weights | N/A | N/A |
| 129 | MI | Phi 4 Mini | 45.0 | 0.0 | 62.5 | 35.6 | N/A | 25.1 | 80.0% | 128K | Open weights | $0.075 | $0.30 |
| 130 | OP | GPT-4.5 | 43.8 | 36.2 | 69.3 | 85.0 | 40.5 | 52.8 | 100.0% | 128K | Closed weights | N/A | N/A |
| 131 | MI | MiniMax M1 40K | 43.4 | 35.3 | N/A | 29.6 | 50.9 | 48.3 | 80.0% | N/A | Closed weights | N/A | N/A |
| 132 | OP | GPT-4o | 42.9 | 23.9 | 30.2 | 19.8 | 10.8 | 23.7 | 100.0% | 128K | Closed weights | $2.5 | $10 |
| 133 | MI | Phi 4 Reasoning Plus | 42.7 | 26.8 | N/A | N/A | 66.3 | 41.5 | 60.0% | N/A | Closed weights | $0.125 | $0.50 |
| 134 | AC | Qwen2.5 VL 72B Instruct | 42.5 | 22.7 | 44.6 | 20.8 | 12.6 | 37.2 | 100.0% | 131.1K | Open weights | N/A | N/A |
| 135 | CO | Command R+ | 42.4 | 0.0 | N/A | 10.6 | N/A | 58.2 | 60.0% | 128K | Closed weights | $0.15 | $0.60 |
| 136 | DE | DeepSeek-V3 0324 | 42.1 | 26.0 | N/A | 32.3 | 36.1 | 41.9 | 80.0% | 163.8K | Closed weights | N/A | N/A |
| 137 | MA | Magistral Small 2506 | 41.6 | 19.8 | N/A | N/A | 41.7 | 15.9 | 60.0% | 131.1K | Open weights | N/A | N/A |
| 138 | MA | Ministral 3 (8B Reasoning 2512) | 40.8 | 29.0 | N/A | N/A | 55.6 | 37.2 | 60.0% | 262.1K | Closed weights | $0.10 | $0.10 |
| 139 | AMNova MicroAmazon | Nova Micro | 40.6 | 4.3 | 0.0 | 38.3 | 17.3 | 13.0 | 100.0% | 128K | Closed weights | $0.035 | $0.14 |
| 140 | ME | LongCat-Flash-Lite | 40.3 | 33.0 | N/A | 69.3 | 29.6 | 37.5 | 80.0% | 256K | Closed weights | N/A | N/A |
| 141 | NV | Llama-3.3 Nemotron Super 49B v1 | 39.5 | 22.4 | N/A | 64.5 | 96.9 | 48.0 | 80.0% | 131.1K | Open weights | N/A | N/A |
| 142 | AC | Qwen2.5-Coder 32B Instruct | 39.4 | 4.4 | N/A | 46.2 | 68.0 | 33.5 | 80.0% | 128K | Closed weights | $0.287 | $0.861 |
| 143 | AC | Qwen3 VL 8B Thinking | 39.3 | 28.5 | 30.8 | 38.2 | 28.8 | 38.3 | 100.0% | 262.1K | Closed weights | N/A | N/A |
| 144 | AC | Qwen3.5-35B-A3B | 39.3 | 52.0 | 52.4 | 59.2 | 42.7 | 58.2 | 100.0% | 262.1K | Open weights | $0.25 | $2 |
| 145 | AC | Qwen3 VL 8B Instruct | 39.2 | 24.8 | 16.0 | 21.0 | 29.3 | 27.1 | 100.0% | 262.1K | Closed weights | N/A | N/A |
| 146 | SA | Sarvam-30B | 39.1 | 34.3 | N/A | 30.5 | 49.6 | 71.8 | 80.0% | 128K | Open weights | N/A | N/A |
| 147 | OP | GPT-4.1 | 38.6 | 31.9 | 64.5 | 26.7 | 37.7 | 39.0 | 100.0% | 1M | Closed weights | $2 | $8 |
| 148 | AN | Claude Opus 4 | 37.7 | 46.4 | 33.3 | N/A | 68.6 | 50.3 | 80.0% | 200K | Closed weights | N/A | N/A |
| 149 | AC | Qwen2.5 VL 7B Instruct | 37.6 | 12.8 | 23.8 | 8.4 | 6.7 | 16.9 | 100.0% | N/A | Closed weights | $0.35 | $1.05 |
| 150 | AC | Qwen3 30B A3B | 37.5 | 32.1 | N/A | N/A | 49.2 | 38.7 | 60.0% | 128K | Closed weights | N/A | N/A |
| 151 | MI | Phi 4 Reasoning | 37.5 | 22.0 | N/A | N/A | 73.6 | 30.5 | 60.0% | N/A | Closed weights | $0.125 | $0.50 |
| 152 | AN | Claude 3 Haiku | 37.0 | 0.0 | N/A | 29.2 | 27.7 | 44.5 | 80.0% | 200K | Closed weights | N/A | N/A |
| 153 | AC | QwQ-32B | 36.5 | 24.8 | N/A | 21.0 | 34.9 | 40.0 | 80.0% | N/A | Closed weights | $0.287 | $0.861 |
| 154 | MA | Mistral Small 4 | 35.9 | 33.4 | N/A | N/A | 73.9 | 36.0 | 60.0% | 256K | Open weights | $0.15 | $0.60 |
| 155 | AMNova 2 LiteAmazon | Nova 2 Lite | 35.7 | 43.0 | N/A | N/A | 35.5 | 73.6 | 60.0% | 1M | Closed weights | $0.33 | $2.75 |
| 156 | OP | GPT-4.1 mini | 35.6 | 24.8 | 58.1 | 28.4 | 13.1 | 30.9 | 100.0% | 1M | Closed weights | $0.40 | $1.6 |
| 157 | GO | Gemini 2.5 Flash-Lite | 35.2 | 19.1 | 59.7 | 3.3 | 9.8 | 36.1 | 100.0% | 1M | Closed weights | $0.10 | $0.40 |
| 158 | ME | Llama 3.2 90B Instruct | 35.0 | 10.8 | 30.6 | 32.5 | N/A | 41.3 | 80.0% | 128K | Closed weights | N/A | N/A |
| 159 | AL | Jamba 1.5 Mini | 34.8 | 0.0 | N/A | 14.9 | N/A | 7.5 | 60.0% | 256.1K | Closed weights | N/A | N/A |
| 160 | NV | Nemotron Nano 9B v2 | 34.3 | 32.4 | N/A | 87.1 | 75.0 | 52.9 | 80.0% | 131.1K | Open weights | N/A | N/A |
| 161 | XI | MiMo-V2.5 | 33.9 | 61.8 | N/A | N/A | 43.8 | 64.3 | 60.0% | 1M | Open weights | $0.14 | $0.28 |
| 162 | GO | Gemini 2.0 Flash | 33.7 | 28.1 | 54.8 | 97.2 | 27.8 | 61.0 | 100.0% | 1M | Closed weights | N/A | N/A |
| 163 | GO | DiffusionGemma 26B-A4B | 33.4 | 34.2 | 45.5 | 34.0 | 18.6 | 40.5 | 100.0% | N/A | Closed weights | N/A | N/A |
| 164 | NV | Llama 3.1 Nemotron 70B Instruct | 33.3 | 3.1 | N/A | 53.2 | N/A | 48.5 | 60.0% | 128K | Open weights | N/A | N/A |
| 165 | CO | Command A+ | 33.1 | 41.9 | 67.7 | 86.8 | 33.3 | 51.8 | 100.0% | 128K | Open weights | $2.5 | $10 |
| 166 | AC | Qwen3 Max | 33.0 | 40.7 | N/A | N/A | 38.0 | 57.6 | 60.0% | 262.1K | Closed weights | $1.2 | $6 |
| 167 | OP | o1-mini | 32.6 | 16.8 | N/A | 12.9 | 90.8 | 59.1 | 80.0% | 128K | Closed weights | N/A | N/A |
| 168 | AC | Qwen2.5 VL 32B Instruct | 32.0 | 17.9 | 49.2 | 38.6 | 49.4 | 15.2 | 100.0% | N/A | Closed weights | N/A | N/A |
| 169 | AC | Qwen3 VL 30B A3B Instruct | 31.7 | 28.8 | 44.0 | 28.7 | 26.8 | 36.7 | 100.0% | 262.1K | Closed weights | N/A | N/A |
| 170 | GO | Gemini 1.5 Pro | 31.3 | 20.5 | 40.3 | 52.0 | 41.5 | 72.8 | 100.0% | 2.1M | Closed weights | N/A | N/A |
| 171 | AC | Qwen2.5 32B Instruct | 30.0 | 14.8 | N/A | 81.1 | 68.3 | 53.6 | 80.0% | N/A | Closed weights | $0.70 | $2.8 |
| 172 | NR | Hermes 3 70B | 29.7 | 8.0 | 35.7 | 34.0 | N/A | 68.8 | 80.0% | 131.1K | Closed weights | N/A | N/A |
| 173 | MI | Phi 4 | 29.6 | 9.4 | N/A | 56.1 | 38.5 | 18.1 | 80.0% | 16K | Closed weights | $0.125 | $0.50 |
| 174 | ME | Llama 3.1 8B Instruct | 29.3 | 0.0 | N/A | 10.3 | 49.2 | 10.2 | 80.0% | 131.1K | Closed weights | N/A | N/A |
| 175 | XA | Grok-2 | 29.2 | 21.0 | 41.9 | 62.4 | 66.9 | 45.3 | 100.0% | 128K | Closed weights | N/A | N/A |
| 176 | ME | Llama 3.2 3B Instruct | 29.1 | 0.0 | N/A | 16.7 | N/A | 10.7 | 60.0% | 128K | Closed weights | N/A | N/A |
| 177 | NV | Llama 3.1 Nemotron Nano 8B V1 | 28.8 | 10.4 | N/A | 45.2 | 84.4 | 14.7 | 80.0% | N/A | Closed weights | N/A | N/A |
| 178 | MA | Pixtral-12B | 28.3 | 0.0 | 11.3 | 23.8 | 16.9 | 20.0 | 100.0% | 128K | Open weights | $0.15 | $0.15 |
| 179 | XA | Grok-1.5V | 28.0 | 1.3 | 13.7 | 11.8 | N/A | N/A | 60.0% | N/A | Closed weights | N/A | N/A |
| 180 | MA | Min istral 3 (3B Reasoning 2512) | 27.9 | 20.8 | N/A | N/A | 48.6 | 26.1 | 60.0% | 131.1K | Closed weights | $0.04 | $0.04 |
| 181 | ME | Llama 3.2 11B Instruct | 27.3 | 0.0 | 8.1 | 16.8 | N/A | 26.1 | 80.0% | 128K | Closed weights | N/A | N/A |
| 182 | AC | Qwen3 VL 4B Thinking | 27.2 | 23.0 | 28.3 | 27.5 | 25.5 | 25.8 | 100.0% | 262.1K | Closed weights | N/A | N/A |
| 183 | GO | Gemini 2.0 Flash-Lite | 26.6 | 21.0 | 43.5 | 86.0 | N/A | 39.7 | 80.0% | 1M | Closed weights | N/A | N/A |
| 184 | XA | Grok-2 mini | 26.0 | 16.3 | 37.1 | 56.1 | 50.8 | 39.8 | 100.0% | N/A | Closed weights | N/A | N/A |
| 185 | GO | Gemini 1.5 Flash | 26.0 | 10.7 | 33.9 | 40.4 | 23.1 | 46.6 | 100.0% | 1M | Closed weights | N/A | N/A |
| 186 | BA | ERNIE 4.5 | 25.9 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1 | 100.0% | 128K | Closed weights | N/A | N/A |
| 187 | MI | Phi-4-multimodal-instruct | 25.6 | 7.4 | 17.7 | 36.8 | N/A | 25.0 | 80.0% | 128K | Closed weights | N/A | N/A |
| 188 | ME | Llama 3.3 70B Instruct | 24.9 | 22.0 | N/A | 68.6 | 66.9 | 68.7 | 80.0% | 128K | Open weights | N/A | N/A |
| 189 | OP | GPT-4.1 nano | 24.0 | 4.3 | 19.4 | 21.1 | 0.0 | 6.1 | 100.0% | 1M | Closed weights | $0.10 | $0.40 |
| 190 | DE | DeepSeek R1 Distill Qwen 7B | 23.2 | 15.7 | N/A | 25.8 | 29.9 | 61.5 | 80.0% | N/A | Closed weights | N/A | N/A |
| 191 | AC | Qwen2 72B Instruct | 22.8 | 9.8 | N/A | 61.0 | 46.6 | 51.9 | 80.0% | N/A | Closed weights | N/A | N/A |
| 192 | DE | DeepSeek R1 Distill Llama 8B | 22.5 | 12.4 | N/A | 9.7 | 31.9 | 46.1 | 80.0% | N/A | Closed weights | N/A | N/A |
| 193 | AC | Qwen2.5 72B Instruct | 22.5 | 20.9 | N/A | 80.1 | 60.3 | 54.9 | 80.0% | 131.1K | Closed weights | $1.4 | $5.6 |
| 194 | GO | Gemma 4 E4B | 22.2 | 24.4 | 18.2 | 25.8 | 18.2 | 31.7 | 100.0% | 131.1K | Open weights | N/A | N/A |
| 195 | AC | Qwen2.5-Omni-7B | 21.8 | 10.2 | 27.7 | 35.3 | 26.1 | 25.1 | 100.0% | N/A | Closed weights | $0.10 | $0.40 |
| 196 | OP | GPT-4 Turbo | 21.5 | 14.6 | N/A | 70.3 | 55.4 | 69.2 | 80.0% | 128K | Closed weights | $10 | $30 |
| 197 | AC | Qwen2.5 14B Instruct | 21.4 | 8.2 | N/A | 62.1 | 51.2 | 32.7 | 80.0% | N/A | Closed weights | $0.35 | $1.4 |
| 198 | GO | Gemma 3n E4B Instructed LiteRT Preview | 21.1 | 0.0 | 41.2 | 31.7 | 16.9 | 29.0 | 100.0% | N/A | Closed weights | N/A | N/A |
| 199 | AMNova 2 OmniAmazon | Nova 2 Omni | 20.9 | 43.9 | N/A | N/A | 48.0 | 59.4 | 60.0% | N/A | Closed weights | N/A | N/A |
| 200 | AC | Qwen3 VL 4B Instruct | 20.8 | 19.3 | 12.1 | 12.9 | 17.8 | 19.6 | 100.0% | 262.1K | Closed weights | N/A | N/A |
| 201 | GO | Gemma 3 27B | 20.4 | 15.8 | 20.0 | 69.1 | 39.2 | 50.1 | 100.0% | 131.1K | Closed weights | N/A | N/A |
| 202 | MA | Mistral Small 3.1 24B Instruct | 18.9 | 8.4 | 53.0 | 40.7 | 59.2 | 19.6 | 100.0% | N/A | Closed weights | N/A | N/A |
| 203 | MI | Phi-3.5-vision-instruct | 18.7 | 0.0 | 3.2 | 2.6 | N/A | 37.5 | 80.0% | N/A | Closed weights | N/A | N/A |
| 204 | AC | Qwen3.5-2B | 18.5 | 2.8 | N/A | N/A | 7.6 | 11.0 | 60.0% | N/A | Closed weights | N/A | N/A |
| 205 | MA | Mistral Small 3 24B Instruct | 18.0 | 7.5 | N/A | 48.6 | 43.9 | 29.1 | 80.0% | 32K | Closed weights | N/A | N/A |
| 206 | MA | Mistral Large 3 (675B Instruct 2512) | 16.9 | 15.8 | N/A | 70.0 | 24.3 | 36.4 | 80.0% | 262.1K | Open weights | $0.50 | $1.5 |
| 207 | DE | DeepSeek VL2 Tiny | 16.6 | 0.0 | 1.6 | 15.8 | N/A | 0.0 | 80.0% | N/A | Closed weights | N/A | N/A |
| 208 | GO | Gemma 3 12B | 14.1 | 11.2 | 10.0 | 57.3 | 32.4 | 51.9 | 100.0% | 131.1K | Closed weights | N/A | N/A |
| 209 | AN | Claude 3.5 Haiku | 13.7 | 9.3 | N/A | 56.8 | 19.9 | 38.0 | 80.0% | 200K | Closed weights | N/A | N/A |
| 210 | GO | Gemini Diffusion | 12.7 | 3.6 | N/A | N/A | 36.8 | 23.2 | 60.0% | N/A | Closed weights | N/A | N/A |
| 211 | AC | Qwen2.5-Coder 7B Instruct | 12.1 | 0.0 | N/A | 19.9 | 50.5 | 16.0 | 80.0% | N/A | Closed weights | $0.144 | $0.287 |
| 212 | OP | GPT-4o mini | 12.0 | 8.1 | 29.0 | 42.9 | 28.5 | 55.3 | 100.0% | 128K | Closed weights | $0.15 | $0.60 |
| 213 | GO | Gemini 1.5 Flash 8B | 11.2 | 0.0 | 16.1 | 24.5 | N/A | 13.1 | 80.0% | 1M | Closed weights | N/A | N/A |
| 214 | GO | Gemma 4 E2B | 11.0 | 11.6 | 9.1 | 19.4 | 8.1 | 19.9 | 100.0% | 131.1K | Open weights | N/A | N/A |
| 215 | AC | Qwen2.5 7B Instruct | 9.4 | 6.5 | N/A | 58.4 | 37.6 | 24.6 | 80.0% | 131.1K | Closed weights | $0.175 | $0.70 |
| 216 | XA | Grok-1.5 | 9.0 | 0.0 | 13.7 | 26.9 | 21.5 | 13.3 | 100.0% | N/A | Closed weights | N/A | N/A |
| 217 | OP | GPT-4 | 8.6 | 4.6 | N/A | 36.3 | 10.8 | 74.9 | 80.0% | 8.2K | Closed weights | $30 | $60 |
| 218 | GO | Gemma 3n E4B Instructed | 8.0 | 0.0 | N/A | 37.5 | 16.9 | 38.2 | 80.0% | 32K | Closed weights | N/A | N/A |
| 219 | OP | GPT-3.5 Turbo | 5.2 | 0.0 | 0.0 | 13.9 | 12.3 | 13.6 | 100.0% | 16.4K | Closed weights | $0.50 | $1.5 |
| 220 | GO | Gemma 3n E2B Instructed LiteRT (Preview) | 5.2 | 0.0 | 15.1 | 12.3 | 7.0 | 12.5 | 100.0% | N/A | Closed weights | N/A | N/A |
| 221 | GO | Gemini 1.0 Pro | 3.4 | 0.0 | 4.8 | 4.1 | N/A | 40.2 | 80.0% | 32.8K | Closed weights | N/A | N/A |
| 222 | AC | Qwen3.5-0.8B | 3.3 | 0.0 | N/A | N/A | 0.0 | 1.2 | 60.0% | N/A | Closed weights | N/A | N/A |
| 223 | AC | Qwen2 7B Instruct | 3.0 | 0.0 | N/A | 14.9 | 17.1 | 17.3 | 80.0% | N/A | Closed weights | N/A | N/A |
| 224 | GO | Gemma 3n E2B Instructed | 1.8 | 0.0 | N/A | 12.5 | 7.0 | 12.4 | 80.0% | N/A | Closed weights | N/A | N/A |
| 225 | GO | Gemma 3 4B | 1.7 | 0.0 | 0.0 | 38.9 | 10.8 | 26.2 | 100.0% | 131.1K | Closed weights | N/A | N/A |
| 226 | GO | Gemma 3 1B | 0.4 | 0.0 | N/A | 6.9 | 1.0 | 2.5 | 80.0% | N/A | Closed weights | N/A | N/A |
| 227 | ZA | GLM-5V-Turbo | 0.0 | 57.0 | N/A | N/A | 80.0 | 16.7 | 60.0% | 200K | Closed weights | $5 | $22 |
Official PAYG prices appear here. Third-party offers remain on the pricing and model detail pages.
Capability at each price point
Official vendor API prices plotted against the reasoning metric used on this page. Price remains a separate decision signal.
Reasoning scoreOfficial API price blend (8:1 input/output), USD / 1M
Efficient frontier101 models with official PAYG prices
Reasoning Ranking Composition
Vendor concentration and model access among the first 25 ranked products.
Top-model vendor mix
25 modelsCompare the leaders
Open focused comparisons between the current leader and the nearest practical alternatives.
About this leaderboard
Common questions about Best AI for Reasoning.
What is the best model on Best AI for Reasoning?
Claude Opus 5 is currently ranked first with a reasoning score of 100.0.
How is this leaderboard ranked?
Each model appears once using its current scored version. Category pages use the capability named in the title, while the overall page uses the LLMBoard score.
How many models are included?
This page currently ranks 227 unique model products.
Where does pricing come from?
Main price columns use the model vendor's official standard PAYG API rate. Eligible third-party offers appear only in separately labeled columns, and unavailable official prices display as N/A.
Does Arena affect the score?
No. Arena results are displayed as an independent signal and are not included in the current LLMBoard capability score.