Benchmarks / Artificial Analysis

Reported by Artificial Analysis

Artificial Analysis

Share of questions answered correctly over long documents, as run by Artificial Analysis with its own harness and prompts.

Last updated 9 Nov 2026

Results dated
20 Oct 2026 to 9 Nov 2026
Results
407 configurations of 241 models
Unit
% of questions
Licence
Artificial Analysis commercial data licence

Artificial Analysis in brief

What it measures. Artificial Analysis is a third-party benchmark, shown here with credit. Measured here: Share of questions answered correctly over long documents, as run by Artificial Analysis with its own harness and prompts.

Latest results. , 407 configurations ranked.

Top 3 on Long-context reasoning (AA-LCR) (% of questions, higher is better):

  1. Kimi K3 (max reasoning) (Moonshot AI): 88.7%
  2. MiMo-V2.6-Pro (Xiaomi): 86.3%
  3. Kimi K3.1 Pro (Moonshot AI): 86.3%

How to cite. Artificial Analysis, via Spring Prompt, results dated 9 November 2026. https://springprompt.com/benchmarks/artificial-analysis These results belong to Artificial Analysis, not to us. Licence: Artificial Analysis commercial data licence. Credit Artificial Analysis first.

Long-context reasoning (AA-LCR): Magistral Small 1.2

Top 15 of 407 results · % of questions, higher is better. Choose a model to highlight it.Clear highlight

  1. 1 Kimi K3 (max reasoning)Moonshot AI 88.7%
  2. 2 MiMo-V2.6-ProXiaomi 86.3%
  3. 2 Kimi K3.1 ProMoonshot AI 86.3%
  4. 4 Claude Fable 5.1 (max reasoning)Anthropic 85.3%
  5. 5 Claude Fable 5.1 (medium reasoning)Anthropic 84.7%
  6. 5 Claude Opus 5.5 (max reasoning)Anthropic 84.7%
  7. 5 Claude Opus 5.5 (extra-high reasoning)Anthropic 84.7%
  8. 8 Claude Opus 5.5 (medium reasoning)Anthropic 84.3%
  9. 8 GPT-5.5 (high reasoning)OpenAI 84.3%
  10. 8 GPT-5.5 (extra-high reasoning)OpenAI 84.3%
  11. 11 DeepSeek-V4.1-Flash (max reasoning)DeepSeek 84.0%
  12. 11 Gemini 3.8 Flash (medium reasoning)Google 84.0%
  13. 11 GPT-5.6 Sol (max reasoning)OpenAI 84.0%
  14. 11 GPT-6.1 Sol (low reasoning)OpenAI 84.0%
  15. 15 Claude Fable 5.1 (high reasoning)Anthropic 83.7%
  16. 366 Magistral Small 1.2Mistral AI 19.3%

Full results

Artificial Analysis: Long-context reasoning (AA-LCR), % of questions, higher is better
#ModelLong-context reasoning (AA-LCR)
% of questions, higher is better
Price
$ per million tokens, in / out
1 Kimi K3 (max reasoning)Moonshot AI
88.7%
$3 / $15
2 MiMo-V2.6-ProXiaomi
86.3%
$0.43 / $0.87
2 Kimi K3.1 ProMoonshot AI
86.3%
$1.75 / $10
4 Claude Fable 5.1 (max reasoning)Anthropic
85.3%
$10 / $50
5 Claude Fable 5.1 (medium reasoning)Anthropic
84.7%
$10 / $50
5 Claude Opus 5.5 (max reasoning)Anthropic
84.7%
$4 / $20
5 Claude Opus 5.5 (extra-high reasoning)Anthropic
84.7%
$4 / $20
8 Claude Opus 5.5 (medium reasoning)Anthropic
84.3%
$4 / $20
8 GPT-5.5 (high reasoning)OpenAI
84.3%
$5 / $30
8 GPT-5.5 (extra-high reasoning)OpenAI
84.3%
$5 / $30
11 DeepSeek-V4.1-Flash (max reasoning)DeepSeek
84.0%
$0.30 / $1.20
11 Gemini 3.8 Flash (medium reasoning)Google
84.0%
$1.50 / $7.50
11 GPT-5.6 Sol (max reasoning)OpenAI
84.0%
$4 / $20
11 GPT-6.1 Sol (low reasoning)OpenAI
84.0%
$2 / $10
15 Claude Fable 5.1 (high reasoning)Anthropic
83.7%
$10 / $50
15 GPT-5.6 Luna (max reasoning)OpenAI
83.7%
$0.20 / $1.20
15 GPT-6 Sol (high reasoning)OpenAI
83.7%
$2 / $10
15 GPT-6 Sol (max reasoning)OpenAI
83.7%
$2 / $10
19 Muse Glimmer (high reasoning)Meta
83.3%
–
19 GPT-5.3-Codex (extra-high reasoning)OpenAI
83.3%
$1.75 / $14
19 GPT-6.1 Sol (medium reasoning)OpenAI
83.3%
$2 / $10
19 GPT-6 Luna (max reasoning)OpenAI
83.3%
$0.10 / $0.50
23 Claude Fable 5.1 (extra-high reasoning)Anthropic
83.0%
$10 / $50
23 Gemini 3.7 Flash (medium reasoning)Google
83.0%
$1.50 / $7.50
23 Muse Spark 1.3 (max reasoning)Meta
83.0%
$1.25 / $4.25
23 Muse Spark 1.3 (extra-high reasoning)Meta
83.0%
$1.25 / $4.25
23 MiniMax-M3MiniMax
83.0%
$0.30 / $1.20
23 GPT-5.5 (medium reasoning)OpenAI
83.0%
$5 / $30
23 GPT-5.6 Terra (max reasoning)OpenAI
83.0%
$2 / $12
23 GPT-6.1 Sol (max reasoning)OpenAI
83.0%
$2 / $10
31 GPT-6.1 Terra (max reasoning)OpenAI
82.7%
$1 / $5
31 Claude Haiku 5.5 (max reasoning)Anthropic
82.7%
$0.10 / $0.50
31 Claude Opus 5.5 (high reasoning)Anthropic
82.7%
$4 / $20
31 Claude Sonnet 5.5 (max reasoning)Anthropic
82.7%
$2 / $10
31 DeepSeek-V4.1-Flash-1017 (max reasoning)DeepSeek
82.7%
$0.30 / $1.20
31 GPT-5.2 (extra-high reasoning)OpenAI
82.7%
$1.75 / $14
37 Claude Fable 5.1 (low reasoning)Anthropic
82.3%
$10 / $50
37 Claude Fable 5 (max reasoning)Anthropic
82.3%
$10 / $50
37 GPT-5.2-Codex (extra-high reasoning)OpenAI
82.3%
$1.75 / $14
37 GPT-5.6 Sol (extra-high reasoning)OpenAI
82.3%
$4 / $20
37 GPT-6.1 Sol (high reasoning)OpenAI
82.3%
$2 / $10
37 GPT-6 Sol (medium reasoning)OpenAI
82.3%
$2 / $10
37 GPT-6.1 Terra (high reasoning)OpenAI
82.3%
$1 / $5
44 Qwen3.8-27B (extra-high reasoning)Alibaba
82.0%
$0.50 / $3
44 Claude Opus 5 (medium reasoning)Anthropic
82.0%
$5 / $25
44 Claude Sonnet 5 (max reasoning)Anthropic
82.0%
$2 / $10
44 Gemini 3.1 Pro PreviewGoogle
82.0%
$2 / $12
44 GPT-5.4 (extra-high reasoning)OpenAI
82.0%
$2.50 / $15
49 GPT-6.1 Terra (extra-high reasoning)OpenAI
81.7%
$1 / $5
49 Gemini 3.7 Flash (high reasoning)Google
81.7%
$1.50 / $7.50
49 GPT-5.6 Luna (extra-high reasoning)OpenAI
81.7%
$0.20 / $1.20
49 GPT-5.6 Sol (high reasoning)OpenAI
81.7%
$4 / $20
53 Claude Opus 5 (low reasoning)Anthropic
81.3%
$5 / $25
53 DeepSeek-V4-Flash-Vision-Exp (max reasoning)DeepSeek
81.3%
$0.22 / $0.65
53 Gemini 3.8 Flash (high reasoning)Google
81.3%
$1.50 / $7.50
53 Mistral Large 4Mistral AI
81.3%
$1.36 / $4.18
53 GPT-6 Sol (extra-high reasoning)OpenAI
81.3%
$2 / $10
58 Kimi K2.6Moonshot AI
81.0%
$0.95 / $4
58 GPT-5.5 (low reasoning)OpenAI
81.0%
$5 / $30
58 GPT-6.1 Terra (low reasoning)OpenAI
81.0%
$1 / $5
58 Grok 4.6 (medium reasoning)xAI
81.0%
$2 / $6
58 Grok 4.6 (extra-high reasoning)xAI
81.0%
$2 / $6
63 GPT-6.1 Terra (medium reasoning)OpenAI
80.7%
$1 / $5
63 Qwen3.6-Max-PreviewAlibaba
80.7%
–
63 Claude Opus 5.5 (low reasoning)Anthropic
80.7%
$4 / $20
63 Gemini 3.8 Flash (low reasoning)Google
80.7%
$1.50 / $7.50
63 Muse Wonder (max reasoning)Meta
80.7%
$4 / $20
63 GPT-6 Astra (max reasoning)OpenAI
80.7%
$10 / $50
63 Grok 4.6 (low reasoning)xAI
80.7%
$2 / $6
70 Qwen3.8-2.4T-A95BAlibaba
80.3%
$2 / $6
70 Qwen3.8-Max (0902)Alibaba
80.3%
$2 / $6
70 Claude Opus 5 (extra-high reasoning)Anthropic
80.3%
$5 / $25
70 DeepSeek-V4-Pro (0813, max reasoning)DeepSeek
80.3%
$1.32 / $3.96
70 GPT-5.6 Luna (high reasoning)OpenAI
80.3%
$0.20 / $1.20
70 GPT-5.6 Sol (medium reasoning)OpenAI
80.3%
$4 / $20
70 Grok 4.6 (high reasoning)xAI
80.3%
$2 / $6
77 Claude Sonnet 4.6 (max reasoning)Anthropic
80.0%
$3 / $15
77 Gemini 3.6 Flash (high reasoning)Google
80.0%
$1.50 / $7.50
77 GPT-5.1 (high reasoning)OpenAI
80.0%
$1.25 / $10
77 GPT-6 Astra (high reasoning)OpenAI
80.0%
$10 / $50
77 GPT-6 Astra (low reasoning)OpenAI
80.0%
$10 / $50
77 GPT-6 Astra (extra-high reasoning)OpenAI
80.0%
$10 / $50
77 GPT-6 Luna (extra-high reasoning)OpenAI
80.0%
$0.10 / $0.50
77 Grok 4.7 (low reasoning)xAI
80.0%
$2 / $6
77 GLM-5.3-FlashZ.ai
80.0%
$0.15 / $0.50
86 Qwen3.8-27B (medium reasoning)Alibaba
79.7%
$0.50 / $3
86 Qwen3.8-Flash-NextAlibaba
79.7%
–
86 Claude Sonnet 5.5 (extra-high reasoning)Anthropic
79.7%
$2 / $10
86 DeepSeek-V4-Flash (0731, max reasoning)DeepSeek
79.7%
$0.13 / $0.40
86 Gemini 4 Argon (high reasoning)Google
79.7%
$2 / $10
86 MiniMax M3.1 FlashMiniMax
79.7%
$0.15 / $0.60
86 GPT-6.1 Sol (extra-high reasoning)OpenAI
79.7%
$2 / $10
86 GPT-6 Astra (medium reasoning)OpenAI
79.7%
$10 / $50
86 MiMo-V2.5-Pro (reasoning on)Xiaomi
79.7%
$0.43 / $0.87
86 GLM-5.3 (max reasoning)Z.ai
79.7%
$1.40 / $4.40
96 Claude Opus 5 (max reasoning)Anthropic
79.3%
$5 / $25
96 Kimi K2.7 CodeMoonshot AI
79.3%
$0.95 / $4
96 Kimi K3 (low reasoning)Moonshot AI
79.3%
$3 / $15
96 GPT-6 Luna (high reasoning)OpenAI
79.3%
$0.10 / $0.50
96 GPT-6 Sol (low reasoning)OpenAI
79.3%
$2 / $10
96 Grok 4.5 (high reasoning)xAI
79.3%
$2 / $6
102 Qwen3.7-MaxAlibaba
79.0%
$1.48 / $4.42
102 Claude Opus 5 (high reasoning)Anthropic
79.0%
$5 / $25
102 Muse Spark 1.2 (extra-high reasoning)Meta
79.0%
$1.25 / $4.25
102 GPT-5.6 Terra (extra-high reasoning)OpenAI
79.0%
$2 / $12
102 Hy3Tencent
79.0%
$0.14 / $0.58
107 Claude Opus 4.7 (max reasoning)Anthropic
78.7%
$5 / $25
107 Gemini 3.7 Flash (low reasoning)Google
78.7%
$1.50 / $7.50
109 Qwen3.6-PlusAlibaba
78.3%
$0.33 / $1.95
109 Qwen3.8-Max (0803)Alibaba
78.3%
–
109 Claude Haiku 5.5 (extra-high reasoning)Anthropic
78.3%
$0.10 / $0.50
109 Muse Spark Open (extra-high reasoning)Meta
78.3%
$1.25 / $4.25
109 MiniMax-M2.7MiniMax
78.3%
$0.30 / $1.20
109 GPT-6 Luna (medium reasoning)OpenAI
78.3%
$0.10 / $0.50
109 GLM-5.2 (max reasoning)Z.ai
78.3%
$1.40 / $4.40
116 GPT-5 (high reasoning)OpenAI
78.2%
$1.25 / $10
117 Claude Opus 4.6 (max reasoning)Anthropic
78.0%
$5 / $25
117 Claude Sonnet 5.5 (high reasoning)Anthropic
78.0%
$2 / $10
117 Gemini 3 Flash Preview (reasoning on)Google
78.0%
$0.50 / $3
117 Muse SparkMeta
78.0%
–
117 Kimi K2.5Moonshot AI
78.0%
$0.57 / $2.85
117 GPT-5.6 Sol (low reasoning)OpenAI
78.0%
$4 / $20
117 Beam 1.0 501B A23BReflection
78.0%
$0.40 / $1.20
124 Qwen3.5-27BAlibaba
77.7%
$0.27 / $2.16
124 Claude Opus 4.8 (max reasoning)Anthropic
77.7%
$5 / $25
124 Muse Spark 1.1 (extra-high reasoning)Meta
77.7%
$1.25 / $4.25
124 GPT-5.6 Terra (high reasoning)OpenAI
77.7%
$2 / $12
128 Qwen3.5-397B-A17BAlibaba
77.3%
$0.55 / $3.50
128 Qwen3.6-27BAlibaba
77.3%
$0.30 / $3.20
128 Qwen3.8-27B (low reasoning)Alibaba
77.3%
$0.50 / $3
128 Claude Haiku 5.5 (high reasoning)Anthropic
77.3%
$0.10 / $0.50
128 Claude Haiku 5.5 (medium reasoning)Anthropic
77.3%
$0.10 / $0.50
128 Claude Opus 4.5 (reasoning on)Anthropic
77.3%
$5 / $25
128 Inkling (extra-high reasoning)Thinking Machines
77.3%
$1 / $4.05
135 GPT-5.4 mini (extra-high reasoning)OpenAI
77.0%
$0.75 / $4.50
135 Grok 4.7 (high reasoning)xAI
77.0%
$2 / $6
137 Claude Sonnet 5 (high reasoning)Anthropic
76.7%
$2 / $10
137 Claude Sonnet 5 (extra-high reasoning)Anthropic
76.7%
$2 / $10
137 GPT-5.4 nano (extra-high reasoning)OpenAI
76.7%
$0.20 / $1.25
137 GPT-5.4 (low reasoning)OpenAI
76.7%
$2.50 / $15
137 Grok 4.7 (extra-high reasoning)xAI
76.7%
$2 / $6
142 Qwen3.5-122B-A10BAlibaba
76.3%
$0.26 / $2.08
142 Claude Sonnet 5.5 (medium reasoning)Anthropic
76.3%
$2 / $10
144 Claude Opus 4.1 (reasoning on)Anthropic
76.0%
$15 / $75
144 Claude Sonnet 5.5 (low reasoning)Anthropic
76.0%
$2 / $10
144 Gemini 3.5 Flash-LiteGoogle
76.0%
$0.30 / $2.50
144 Gemini 3 Pro Preview (high reasoning)Google
76.0%
–
144 GPT-5 (medium reasoning)OpenAI
76.0%
$1.25 / $10
149 Claude Opus 4.7 (no reasoning)Anthropic
75.7%
$5 / $25
149 Inkling SmallThinking Machines
75.7%
$0.45 / $1.20
149 GLM-5Z.ai
75.7%
$1 / $3.20
152 GPT-5.6 Luna (medium reasoning)OpenAI
75.0%
$0.20 / $1.20
152 Grok 4.3 (medium reasoning)xAI
75.0%
$1.25 / $2.50
154 DeepSeek-V4-Pro (0423, max reasoning)DeepSeek
74.7%
$1.42 / $2.83
154 o3OpenAI
74.7%
$2 / $8
154 Grok Build 0.1xAI
74.7%
$1 / $2
157 Qwen3-Max-ThinkingAlibaba
74.3%
–
157 Claude Haiku 4.5 (reasoning on)Anthropic
74.3%
$1 / $5
157 DeepSeek-V4-Flash (0423, max reasoning)DeepSeek
74.3%
$0.05 / $0.45
157 Gemini 3.1 Flash-Lite PreviewGoogle
74.3%
$0.25 / $1.50
157 Gemini 3.5 Flash (medium reasoning)Google
74.3%
$1.50 / $9
157 MiMo-V2.6-FlashXiaomi
74.3%
$0.14 / $0.28
163 Gemini 3 Pro Preview (low reasoning)Google
74.0%
–
163 GPT-5.6 Terra (medium reasoning)OpenAI
74.0%
$2 / $12
163 GPT-6 Luna (low reasoning)OpenAI
74.0%
$0.10 / $0.50
163 Grok 4.1 Fast (reasoning)xAI
74.0%
–
163 Grok 4.3 (low reasoning)xAI
74.0%
$1.25 / $2.50
168 Claude Sonnet 5 (medium reasoning)Anthropic
73.7%
$2 / $10
168 Grok 4 Fast (reasoning)xAI
73.7%
–
168 GLM-5.1Z.ai
73.7%
$1.33 / $4.18
171 DeepSeek-V3.2 (reasoning on)DeepSeek
73.3%
$0.28 / $0.42
171 Gemini 3.5 Flash (high reasoning)Google
73.3%
$1.50 / $9
171 MiniMax-M2.5MiniMax
73.3%
$0.29 / $1.20
174 Qwen3.7-PlusAlibaba
73.0%
$0.32 / $1.28
174 Grok 4.3 (high reasoning)xAI
73.0%
$1.25 / $2.50
174 MiMo-V2.5Xiaomi
73.0%
$0.40 / $2
177 GLM-5.3 (low reasoning)Z.ai
72.7%
$1.40 / $4.40
178 Claude Sonnet 4.5 (reasoning on)Anthropic
72.3%
$3 / $15
178 DeepSeek-V3.2-Exp (reasoning on)DeepSeek
72.3%
$0.27 / $0.41
178 GPT-5 mini (high reasoning)OpenAI
72.3%
$0.25 / $2
178 GPT-5 mini (medium reasoning)OpenAI
72.3%
$0.25 / $2
182 Qwen3-235B-A22B-Thinking-2507Alibaba
72.0%
$0.45 / $3.50
182 Qwen3.5-35B-A3BAlibaba
72.0%
$0.15 / $1
182 Claude Haiku 5.5 (low reasoning)Anthropic
72.0%
$0.10 / $0.50
182 DeepSeek-V4-Flash (0423, high reasoning)DeepSeek
72.0%
$0.05 / $0.45
182 Kimi K2 ThinkingMoonshot AI
72.0%
$0.60 / $2.50
187 Qwen3.6-35B-A3BAlibaba
71.7%
$0.10 / $0.95
187 GPT-5-Codex (high reasoning)OpenAI
71.7%
–
187 GLM-5-TurboZ.ai
71.7%
$1.20 / $4
190 GPT-5.6 Terra (low reasoning)OpenAI
71.3%
$2 / $12
191 Gemini 2.5 Flash Preview (09-2025, reasoning on)Google
71.0%
–
191 GLM-4.7Z.ai
71.0%
$0.60 / $2.20
193 Claude Opus 4.5 (no reasoning)Anthropic
70.7%
$5 / $25
193 Solar Pro 4Upstage
70.7%
$0.15 / $0.60
195 Claude Sonnet 4 (reasoning on)Anthropic
70.3%
–
195 DeepSeek-V4-Pro (0423, high reasoning)DeepSeek
70.3%
$1.42 / $2.83
195 GPT-5.2 (medium reasoning)OpenAI
70.3%
$1.75 / $14
195 GLM-5V-TurboZ.ai
70.3%
$1.20 / $4
199 Qwen3.5-9BAlibaba
70.0%
$0.10 / $0.15
199 Claude Sonnet 5 (no reasoning)Anthropic
70.0%
$2 / $10
199 DeepSeek-V3.2-SpecialeDeepSeek
70.0%
–
199 GPT-5.5 Instant (2026-06-26)OpenAI
70.0%
–
199 GPT-5.6 Luna (low reasoning)OpenAI
70.0%
$0.20 / $1.20
204 Gemma 4 31BGoogle
69.7%
$0.15 / $0.40
204 Kimi K2.6 (no reasoning)Moonshot AI
69.7%
$0.95 / $4
206 Qwen3.8-27B (no reasoning)Alibaba
69.3%
$0.50 / $3
206 DeepSeek-V3.1-Terminus (reasoning on)DeepSeek
69.3%
$0.27 / $1
206 Mistral Medium 3.5Mistral AI
69.3%
$1.50 / $7.50
206 GPT-5.1-Codex (high reasoning)OpenAI
69.3%
$1.25 / $10
210 Gemini 2.5 ProGoogle
69.0%
$1.25 / $10
210 Nemotron 3.5 Super VLNVIDIA
69.0%
$0.15 / $0.50
210 Grok 4.20xAI
69.0%
$1.25 / $2.50
213 Claude Sonnet 4.6 (no reasoning)Anthropic
68.3%
$3 / $15
213 GPT-4.1OpenAI
68.3%
$2 / $8
215 Grok 4xAI
68.0%
–
216 GPT-6.1 Terra (no reasoning)OpenAI
67.7%
$1 / $5
216 MiniMax-M2.1MiniMax
67.7%
–
216 Grok 4.20 (0309, reasoning)xAI
67.7%
–
219 Claude Sonnet 5 (low reasoning)Anthropic
67.3%
$2 / $10
219 Kimi K2.5 (no reasoning)Moonshot AI
67.3%
$0.57 / $2.85
219 GPT-5.4 nano (medium reasoning)OpenAI
67.3%
$0.20 / $1.25
222 Claude Opus 4.6 (no reasoning)Anthropic
67.0%
$5 / $25
222 GPT-5.4 mini (medium reasoning)OpenAI
67.0%
$0.75 / $4.50
224 Qwen3.6-27B (no reasoning)Alibaba
66.7%
$0.30 / $3.20
224 GPT-5.1-Codex-Mini (high reasoning)OpenAI
66.7%
$0.25 / $2
226 GPT-5.5 Instant (2026-05-26)OpenAI
66.3%
–
227 Gemma 4 26B A4BGoogle
65.7%
$0.09 / $0.30
227 Nemotron 3 Super 120B A12BNVIDIA
65.7%
$0.08 / $0.45
229 Gemini 2.5 Flash (reasoning on)Google
65.3%
$0.30 / $2.50
230 GPT-5 ChatOpenAI
65.0%
–
230 o1OpenAI
65.0%
–
232 Gemini 2.5 Flash-Lite Preview (09-2025, reasoning on)Google
64.7%
–
232 Hy3 Preview (reasoning on)Tencent
64.7%
$0.18 / $0.60
234 Qwen3.5-397B-A17B (no reasoning)Alibaba
64.3%
$0.55 / $3.50
234 Qwen3.6-35B-A3B (no reasoning)Alibaba
64.3%
$0.10 / $0.95
234 MiniMax-M2MiniMax
64.3%
–
237 Qwen3.5-27B (no reasoning)Alibaba
64.0%
$0.27 / $2.16
237 GPT-5.5 (no reasoning)OpenAI
64.0%
$5 / $30
237 GPT-6 Sol (no reasoning)OpenAI
64.0%
$2 / $10
240 Qwen3.5-Omni-PlusAlibaba
63.7%
–
240 Qwen3-Next-80B-A3B-ThinkingAlibaba
63.7%
–
240 Qwen3-VL-235B-A22B-ThinkingAlibaba
63.7%
–
240 Gemma 4 12BGoogle
63.7%
–
244 Qwen3.5-35B-A3B (no reasoning)Alibaba
63.0%
$0.15 / $1
244 Qwen3.5-4B (reasoning on)Alibaba
63.0%
–
246 GPT-5.6 Sol (no reasoning)OpenAI
62.3%
$4 / $20
247 Qwen3-Max-Thinking-PreviewAlibaba
62.0%
–
248 Qwen3-30B-A3B-Thinking-2507Alibaba
61.3%
–
248 Qwen3.5-122B-A10B (no reasoning)Alibaba
61.3%
$0.26 / $2.08
248 Gemini 3.5 Flash (minimal reasoning)Google
61.3%
$1.50 / $9
251 o4-mini (high reasoning)OpenAI
61.0%
–
252 Nova 2 Lite (high reasoning)Amazon
60.3%
$0.30 / $2.50
253 Nova 2 Lite (medium reasoning)Amazon
60.0%
$0.30 / $2.50
253 Gemini 2.5 Flash Preview (09-2025, no reasoning)Google
60.0%
–
255 GPT-5.6 Terra (no reasoning)OpenAI
58.7%
$2 / $12
256 GPT-5.4 (no reasoning)OpenAI
58.3%
$2.50 / $15
257 DeepSeek-R1DeepSeek
57.7%
–
258 DeepSeek-V4.1-Flash-1017 (no reasoning)DeepSeek
57.3%
$0.30 / $1.20
259 DeepSeek-V3.1 (reasoning on)DeepSeek
56.7%
$0.27 / $1
260 DeepSeek-R1-0528DeepSeek
55.7%
$0.50 / $2.18
260 Gemini 2.5 Flash-Lite (reasoning on)Google
55.7%
$0.10 / $0.40
262 Qwen3-VL-32B-ThinkingAlibaba
55.3%
–
262 DeepSeek-V4.1-Flash (no reasoning)DeepSeek
55.3%
$0.30 / $1.20
262 Gemini 3 Flash Preview (no reasoning)Google
55.3%
$0.50 / $3
265 Nova 2 Lite (low reasoning)Amazon
54.3%
$0.30 / $2.50
266 Claude Sonnet 4.5 (no reasoning)Anthropic
54.0%
$3 / $15
266 GLM-4.6 (reasoning on)Z.ai
54.0%
$0.50 / $2
268 GLM-5.1 (no reasoning)Z.ai
53.3%
$1.33 / $4.18
269 DeepSeek-V4-Pro (0423, no reasoning)DeepSeek
53.0%
$1.42 / $2.83
269 Magistral Medium 1.2Mistral AI
53.0%
–
269 Kimi K2 (0905)Moonshot AI
53.0%
$0.60 / $2.50
269 Kimi K2 (0711)Moonshot AI
53.0%
$0.57 / $2.30
269 Grok Code Fast 1xAI
53.0%
–
274 Qwen3-Next-80B-A3B-InstructAlibaba
52.7%
$0.09 / $1.10
274 GLM-4.5Z.ai
52.7%
$0.60 / $2.20
276 Qwen3.5-Omni-FlashAlibaba
52.0%
–
276 gpt-oss-120b (high reasoning)OpenAI
52.0%
$0.10 / $0.50
278 DeepSeek-V4-Pro (0813, no reasoning)DeepSeek
50.7%
$1.32 / $3.96
279 Qwen3-MaxAlibaba
50.0%
–
279 Llama 4 MaverickMeta
50.0%
$0.35 / $1
279 Step 3.5 FlashStepFun
50.0%
$0.10 / $0.30
282 Gemini 2.5 Flash (no reasoning)Google
49.9%
$0.30 / $2.50
283 Claude Haiku 4.5 (no reasoning)Anthropic
49.7%
$1 / $5
283 Gemini 2.5 Flash-Lite Preview (09-2025, no reasoning)Google
49.7%
–
283 Mistral Small 4Mistral AI
49.7%
$0.15 / $0.60
286 GLM-4.6V (reasoning on)Z.ai
48.7%
$0.30 / $0.90
287 Qwen3-Coder-NextAlibaba
47.0%
$0.12 / $0.80
287 DeepSeek-V3.1 (no reasoning)DeepSeek
47.0%
$0.27 / $1
289 Gemma 4 31B (no reasoning)Google
46.7%
$0.15 / $0.40
289 GLM-4.5-AirZ.ai
46.7%
$0.14 / $0.86
291 Qwen3.5-9B (no reasoning)Alibaba
46.0%
$0.10 / $0.15
291 gpt-oss-120b (low reasoning)OpenAI
46.0%
$0.10 / $0.50
293 Qwen3-Coder-480B-A35BAlibaba
45.7%
$0.30 / $1
293 DeepSeek-V3.2 (no reasoning)DeepSeek
45.7%
$0.28 / $0.42
293 GPT-5.2 (no reasoning)OpenAI
45.7%
$1.75 / $14
296 DeepSeek-V3.1-Terminus (no reasoning)DeepSeek
45.3%
$0.27 / $1
297 Granite 4.2 8BIBM
45.0%
$0.06 / $0.15
297 GPT-5.1 (no reasoning)OpenAI
45.0%
$1.25 / $10
297 GPT-5 nano (high reasoning)OpenAI
45.0%
$0.05 / $0.40
300 DeepSeek-V3.2-Exp (no reasoning)DeepSeek
44.7%
$0.27 / $0.41
301 Claude Sonnet 4 (no reasoning)Anthropic
44.0%
–
301 GPT-4.1 miniOpenAI
44.0%
$0.40 / $1.60
303 Mercury 2Inception
43.7%
–
303 GPT-5 nano (medium reasoning)OpenAI
43.7%
$0.05 / $0.40
303 GLM-5 (no reasoning)Z.ai
43.7%
$1 / $3.20
306 Qwen3-Max-PreviewAlibaba
43.0%
–
306 o3-mini (high reasoning)OpenAI
43.0%
–
308 Mistral Medium 3.1Mistral AI
42.7%
$0.40 / $2
308 GPT-5.6 Luna (no reasoning)OpenAI
42.7%
$0.20 / $1.20
310 Gemma 4 26B A4B (no reasoning)Google
42.3%
$0.09 / $0.30
310 GLM-5.2 (no reasoning)Z.ai
42.3%
$1.40 / $4.40
312 Hy3 Preview (no reasoning)Tencent
42.0%
$0.18 / $0.60
313 DeepSeek-V4-Flash (0423, no reasoning)DeepSeek
41.7%
$0.05 / $0.45
313 MiMo-V2.5-Pro (no reasoning)Xiaomi
41.7%
$0.43 / $0.87
313 GLM-4.7-FlashZ.ai
41.7%
$0.06 / $0.40
316 GPT-4o (2024-08-06)OpenAI
41.0%
$2.50 / $10
317 DeepSeek-V3-0324DeepSeek
40.7%
$0.25 / $1
317 GLM-4.7 (no reasoning)Z.ai
40.7%
$0.60 / $2.20
319 GPT-6 Luna (no reasoning)OpenAI
39.7%
$0.10 / $0.50
320 GPT-5 mini (minimal reasoning)OpenAI
39.3%
$0.25 / $2
321 Trinity Large ThinkingArcee AI
38.0%
–
321 Nemotron 3 Nano 30B A3B (reasoning on)NVIDIA
38.0%
$0.06 / $0.24
323 Qwen3-4B-Thinking-2507Alibaba
37.3%
–
324 GPT-5.4 mini (no reasoning)OpenAI
37.0%
$0.75 / $4.50
325 Mistral Large 3Mistral AI
36.0%
$0.50 / $1.50
326 Gemma 4 12B (no reasoning)Google
35.0%
–
327 Qwen3.5-4B (no reasoning)Alibaba
34.7%
–
327 gpt-oss-20b (high reasoning)OpenAI
34.7%
$0.03 / $0.14
329 Qwen3-235B-A22B-Instruct-2507Alibaba
33.9%
$0.15 / $0.75
330 Qwen3-VL-8B-ThinkingAlibaba
33.3%
–
331 Qwen3-Coder-30B-A3B-InstructAlibaba
32.7%
$0.07 / $0.28
331 Qwen3-VL-235B-A22B-InstructAlibaba
32.7%
$0.21 / $1.90
333 Devstral 2Mistral AI
32.3%
$0.40 / $2
333 Solar Pro 3Upstage
32.3%
–
333 Grok 4.3 (no reasoning)xAI
32.3%
$1.25 / $2.50
336 Gemini 2.5 Flash-Lite (no reasoning)Google
32.0%
$0.10 / $0.40
336 Gemma 4 E4BGoogle
32.0%
–
336 Devstral MediumMistral AI
32.0%
–
339 Mistral Medium 3Mistral AI
31.3%
$0.40 / $2
339 Grok 4.1 Fast (non-reasoning, no reasoning)xAI
31.3%
–
341 gpt-oss-20b (low reasoning)OpenAI
31.0%
$0.03 / $0.14
342 GPT-5.4 nano (no reasoning)OpenAI
29.7%
$0.20 / $1.25
343 DeepSeek-V3DeepSeek
29.3%
$0.26 / $1.03
344 Mistral Small 4 (no reasoning)Mistral AI
28.3%
$0.15 / $0.60
345 Devstral Small 2Mistral AI
28.0%
–
345 Kimi Linear 48B A3B InstructMoonshot AI
28.0%
–
347 Llama 4 ScoutMeta
27.7%
$0.10 / $0.30
348 Qwen3-30B-A3B-Instruct-2507Alibaba
26.3%
$0.09 / $0.30
348 Ministral 3 14BMistral AI
26.3%
$0.20 / $0.20
348 GLM-4.6 (no reasoning)Z.ai
26.3%
$0.50 / $2
351 Ministral 3 8BMistral AI
25.7%
$0.15 / $0.15
352 Grok 4.20 (0309, non-reasoning, no reasoning)xAI
25.3%
–
353 Gemma 4 E4B (no reasoning)Google
24.0%
–
353 Grok 4 Fast (non-reasoning, no reasoning)xAI
24.0%
–
355 Grok 4.20 (no reasoning)xAI
23.3%
$1.25 / $2.50
356 Mistral Small 3.1 24BMistral AI
22.3%
$0.35 / $0.56
357 Qwen3-VL-4B-ThinkingAlibaba
21.3%
–
357 Command ACohere
21.3%
$2.50 / $10
359 Qwen3.5-2B (reasoning on)Alibaba
21.0%
–
359 Nova Pro 1.0Amazon
21.0%
$0.80 / $3.20
361 Mistral Small 3.2 24BMistral AI
20.3%
$0.094 / $0.25
361 GPT-4.1 nanoOpenAI
20.3%
$0.10 / $0.40
361 GLM-4.7-Flash (no reasoning)Z.ai
20.3%
$0.06 / $0.40
364 GPT-5 nano (minimal reasoning)OpenAI
20.0%
$0.05 / $0.40
365 DiffusionGemma 26B A4BGoogle
19.7%
–
366 Magistral Small 1.2Mistral AI
19.3%
–
367 Nova Lite 1.0Amazon
19.0%
$0.06 / $0.24
368 Nova 2 Lite (no reasoning)Amazon
18.7%
$0.30 / $2.50
368 Devstral Small 1.1Mistral AI
18.7%
–
370 Llama 3.1 8B InstructMeta
18.0%
$0.05 / $0.08
371 Ministral 3 3BMistral AI
17.0%
$0.10 / $0.10
371 GLM-4.6V (no reasoning)Z.ai
17.0%
$0.30 / $0.90
373 Qwen3-VL-8B-InstructAlibaba
16.7%
$0.25 / $0.75
374 Gemma 4 E2B (no reasoning)Google
16.3%
–
374 Gemma 4 E2BGoogle
16.3%
–
376 Llama 3.3 70B InstructMeta
15.7%
$0.71 / $0.71
377 Qwen3.5-2B (no reasoning)Alibaba
14.0%
–
377 Qwen3-VL-4B-InstructAlibaba
14.0%
–
379 Nova Micro 1.0Amazon
13.0%
$0.035 / $0.14
380 Qwen3-4B-Instruct-2507Alibaba
11.3%
–
381 Nemotron 3 Nano 30B A3B (no reasoning)NVIDIA
10.7%
$0.06 / $0.24
382 Qwen3.5-0.8B (reasoning on)Alibaba
9.0%
–
383 Gemma 3 12BGoogle
8.3%
$0.05 / $0.15
384 Qwen3.5-0.8B (no reasoning)Alibaba
8.0%
–
385 Gemma 3 27BGoogle
7.3%
$0.08 / $0.35
386 Gemma 3 4BGoogle
6.7%
$0.04 / $0.05
386 Llama 3.2 1B InstructMeta
6.7%
$0.027 / $0.20
388 Llama 3.2 3B InstructMeta
4.3%
$0.05 / $0.33
389 Mistral Large 2 (2407)Mistral AI
2.0%
$2 / $6
390 Qwen3-14B (no reasoning)Alibaba
0.0%
$0.10 / $0.22
390 Qwen3-14B (reasoning on)Alibaba
0.0%
$0.10 / $0.22
390 Qwen3-235B-A22B (no reasoning)Alibaba
0.0%
–
390 Qwen3-235B-A22B (reasoning on)Alibaba
0.0%
–
390 Qwen3-30B-A3B (no reasoning)Alibaba
0.0%
$0.12 / $0.50
390 Qwen3-30B-A3B (reasoning on)Alibaba
0.0%
$0.12 / $0.50
390 Qwen3-32B (no reasoning)Alibaba
0.0%
$0.14 / $0.40
390 Qwen3-32B (reasoning on)Alibaba
0.0%
$0.14 / $0.40
390 Qwen3-8B (no reasoning)Alibaba
0.0%
–
390 Qwen3-8B (reasoning on)Alibaba
0.0%
–
390 Qwen3-Omni-30B-A3B-InstructAlibaba
0.0%
–
390 Qwen3-Omni-30B-A3B-ThinkingAlibaba
0.0%
–
390 Gemma 3 270MGoogle
0.0%
–
390 Phi-4Microsoft
0.0%
$0.07 / $0.14
390 Mistral Small 3Mistral AI
0.0%
$0.05 / $0.08
390 Reka Flash 3Reka AI
0.0%
$0.10 / $0.20
390 GLM-4.5V (no reasoning)Z.ai
0.0%
$0.60 / $1.80
390 GLM-4.5V (reasoning on)Z.ai
0.0%
$0.60 / $1.80

Swipe the table sideways for more columns.

Source: Artificial Analysis, via Spring Prompt, springprompt.com/benchmarks/artificial-analysis. Test your own prompt on these models →

Ranks follow the score as shown, so equal numbers share a rank. Results as published by Artificial Analysis; we do not re-run them.

Progress over time

Long-context reasoning (AA-LCR), plotted at each model's release date, higher is better. Each model counts once, at its best setting. Scores are today's, not launch day's. Hover or tap a mark for its model.

Best score so far

Every model at its release date. The line moves each time a new release beats every earlier one, and each new best is named where there is room.

0%50%100% 2025Jul2026Jul Llama 3.1 8B InstructGPT-4o (2024-08-06)o1Gemini 2.5 Proo3Claude Opus 4.1GPT-5GPT-5.1GPT-5.2GPT-5.3-CodexGPT-5.5Kimi K3

Best score by lab

Each lab's best so far, stepping whenever one of its releases beats its own earlier models. The 6 labs with the best scores today; 19 others not drawn.

Moonshot AIXiaomiAnthropicOpenAIDeepSeekGoogle

0%20%40%60%80%100% 2025Jul2026Jul Moonshot AIXiaomiAnthropicOpenAIDeepSeekGoogle

What it measures

Share of questions answered correctly over long documents, as run by Artificial Analysis with its own harness and prompts.

What it does not measure

Not retrieval over your own document store.

291 results from Artificial Analysis not ranked here · show why

We rank a result only when we can tie it to a specific model you can use. These are left out:

  • Not on sale through the API providers we track: 276
  • A different snapshot or variant from the model we list: 14
  • An unusual combination of settings: 1

Data sourced from Artificial Analysis. Licence: Artificial Analysis commercial data licence.