Benchmarks / Artificial Analysis

Reported by Artificial Analysis

Artificial Analysis

Share of scientific coding sub-problems solved, 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
205 configurations of 121 models
Unit
% of problems
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 scientific coding sub-problems solved, as run by Artificial Analysis with its own harness and prompts.

Latest results. , 205 configurations ranked.

Top 3 on SciCode (% of problems, higher is better):

  1. Claude Opus 5.5 (max reasoning) (Anthropic): 66.9%
  2. Claude Opus 5.5 (extra-high reasoning) (Anthropic): 65.0%
  3. Claude Fable 5.1 (max reasoning) (Anthropic): 63.1%

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.

SciCode: Kimi K2.6

Top 15 of 205 results · % of problems, higher is better. Choose a model to highlight it.Clear highlight

  1. 1 Claude Opus 5.5 (max reasoning)Anthropic 66.9%
  2. 2 Claude Opus 5.5 (extra-high reasoning)Anthropic 65.0%
  3. 3 Claude Fable 5.1 (max reasoning)Anthropic 63.1%
  4. 4 Gemini 4 Argon (high reasoning)Google 61.8%
  5. 5 Claude Fable 5 (max reasoning)Anthropic 61.0%
  6. 5 Claude Sonnet 5.5 (max reasoning)Anthropic 61.0%
  7. 7 Claude Fable 5.1 (extra-high reasoning)Anthropic 60.9%
  8. 7 MiMo-V2.6-ProXiaomi 60.9%
  9. 9 Kimi K3.1 ProMoonshot AI 60.8%
  10. 10 Claude Opus 5.5 (high reasoning)Anthropic 60.4%
  11. 11 Muse Wonder (max reasoning)Meta 60.3%
  12. 12 Gemini 3.7 Flash (medium reasoning)Google 59.8%
  13. 13 Muse Spark 1.3 (extra-high reasoning)Meta 59.7%
  14. 14 Kimi K3 (max reasoning)Moonshot AI 59.5%
  15. 15 Claude Opus 5.5 (medium reasoning)Anthropic 59.3%
  16. 98 Kimi K2.6Moonshot AI 51.5%

Full results

Artificial Analysis: SciCode, % of problems, higher is better
#ModelSciCode
% of problems, higher is better
Price
$ per million tokens, in / out
1 Claude Opus 5.5 (max reasoning)Anthropic
66.9%
$4 / $20
2 Claude Opus 5.5 (extra-high reasoning)Anthropic
65.0%
$4 / $20
3 Claude Fable 5.1 (max reasoning)Anthropic
63.1%
$10 / $50
4 Gemini 4 Argon (high reasoning)Google
61.8%
$2 / $10
5 Claude Fable 5 (max reasoning)Anthropic
61.0%
$10 / $50
5 Claude Sonnet 5.5 (max reasoning)Anthropic
61.0%
$2 / $10
7 Claude Fable 5.1 (extra-high reasoning)Anthropic
60.9%
$10 / $50
7 MiMo-V2.6-ProXiaomi
60.9%
$0.43 / $0.87
9 Kimi K3.1 ProMoonshot AI
60.8%
$1.75 / $10
10 Claude Opus 5.5 (high reasoning)Anthropic
60.4%
$4 / $20
11 Muse Wonder (max reasoning)Meta
60.3%
$4 / $20
12 Gemini 3.7 Flash (medium reasoning)Google
59.8%
$1.50 / $7.50
13 Muse Spark 1.3 (extra-high reasoning)Meta
59.7%
$1.25 / $4.25
14 Kimi K3 (max reasoning)Moonshot AI
59.5%
$3 / $15
15 Claude Opus 5.5 (medium reasoning)Anthropic
59.3%
$4 / $20
16 GLM-5.3 (max reasoning)Z.ai
59.0%
$1.40 / $4.40
17 Muse Spark 1.1 (extra-high reasoning)Meta
58.8%
$1.25 / $4.25
17 Muse Spark 1.3 (max reasoning)Meta
58.8%
$1.25 / $4.25
19 Claude Fable 5.1 (high reasoning)Anthropic
58.7%
$10 / $50
19 Gemini 3.1 Pro PreviewGoogle
58.7%
$2 / $12
21 Claude Opus 5.5 (low reasoning)Anthropic
58.6%
$4 / $20
22 Muse Spark Open (extra-high reasoning)Meta
58.4%
$1.25 / $4.25
23 GPT-5.6 Sol (high reasoning)OpenAI
57.8%
$4 / $20
23 Grok 4.7 (high reasoning)xAI
57.8%
$2 / $6
25 GPT-6 Sol (max reasoning)OpenAI
57.6%
$2 / $10
26 Muse Spark 1.2 (extra-high reasoning)Meta
57.4%
$1.25 / $4.25
26 GPT-5.6 Sol (medium reasoning)OpenAI
57.4%
$4 / $20
26 Grok 4.7 (extra-high reasoning)xAI
57.4%
$2 / $6
29 Claude Sonnet 5.5 (extra-high reasoning)Anthropic
57.3%
$2 / $10
30 Gemini 3.7 Flash (high reasoning)Google
57.2%
$1.50 / $7.50
31 GPT-5.6 Sol (max reasoning)OpenAI
57.1%
$4 / $20
31 GPT-5.6 Sol (extra-high reasoning)OpenAI
57.1%
$4 / $20
33 Claude Fable 5.1 (low reasoning)Anthropic
56.7%
$10 / $50
34 Gemini 3.8 Flash (high reasoning)Google
56.6%
$1.50 / $7.50
35 GPT-6 Astra (max reasoning)OpenAI
56.5%
$10 / $50
35 Grok 4.6 (high reasoning)xAI
56.5%
$2 / $6
37 Claude Fable 5.1 (medium reasoning)Anthropic
56.4%
$10 / $50
37 Claude Opus 5 (max reasoning)Anthropic
56.4%
$5 / $25
37 GPT-5.6 Sol (low reasoning)OpenAI
56.4%
$4 / $20
40 GPT-5.5 (high reasoning)OpenAI
56.1%
$5 / $30
41 DeepSeek-V4.1-Flash-1017 (max reasoning)DeepSeek
55.9%
$0.30 / $1.20
41 Grok 4.6 (medium reasoning)xAI
55.9%
$2 / $6
43 GPT-5.5 (extra-high reasoning)OpenAI
55.8%
$5 / $30
43 GPT-6.1 Sol (high reasoning)OpenAI
55.8%
$2 / $10
45 Claude Opus 5 (extra-high reasoning)Anthropic
55.7%
$5 / $25
45 Gemini 3.7 Flash (low reasoning)Google
55.7%
$1.50 / $7.50
45 GPT-6.1 Sol (extra-high reasoning)OpenAI
55.7%
$2 / $10
45 GPT-6 Astra (extra-high reasoning)OpenAI
55.7%
$10 / $50
49 Claude Opus 5 (high reasoning)Anthropic
55.4%
$5 / $25
49 GPT-6 Astra (high reasoning)OpenAI
55.4%
$10 / $50
51 Gemini 3.8 Flash (medium reasoning)Google
55.1%
$1.50 / $7.50
51 GPT-6.1 Terra (max reasoning)OpenAI
55.1%
$1 / $5
51 GPT-6 Sol (extra-high reasoning)OpenAI
55.1%
$2 / $10
54 Claude Haiku 5.5 (max reasoning)Anthropic
55.0%
$0.10 / $0.50
54 Gemini 3.8 Flash (low reasoning)Google
55.0%
$1.50 / $7.50
54 GPT-5.6 Terra (max reasoning)OpenAI
55.0%
$2 / $12
54 Grok 4.5 (high reasoning)xAI
55.0%
$2 / $6
58 GPT-6 Sol (high reasoning)OpenAI
54.9%
$2 / $10
58 Grok 4.7 (low reasoning)xAI
54.9%
$2 / $6
60 GPT-6 Luna (max reasoning)OpenAI
54.6%
$0.10 / $0.50
61 GPT-5.5 (medium reasoning)OpenAI
54.5%
$5 / $30
62 Claude Opus 4.8 (max reasoning)Anthropic
54.4%
$5 / $25
63 Claude Sonnet 5 (high reasoning)Anthropic
54.3%
$2 / $10
63 Claude Sonnet 5 (max reasoning)Anthropic
54.3%
$2 / $10
65 Mistral Large 4Mistral AI
54.2%
$1.36 / $4.18
65 GPT-6.1 Sol (max reasoning)OpenAI
54.2%
$2 / $10
65 GPT-6 Astra (medium reasoning)OpenAI
54.2%
$10 / $50
68 Qwen3.8-2.4T-A95BAlibaba
54.1%
$2 / $6
68 Claude Sonnet 5 (extra-high reasoning)Anthropic
54.1%
$2 / $10
68 GPT-6 Astra (low reasoning)OpenAI
54.1%
$10 / $50
71 Gemini 3.5 Flash (high reasoning)Google
53.9%
$1.50 / $9
72 GPT-6 Sol (medium reasoning)OpenAI
53.8%
$2 / $10
73 Claude Sonnet 5.5 (high reasoning)Anthropic
53.7%
$2 / $10
74 GPT-5.6 Luna (max reasoning)OpenAI
53.6%
$0.20 / $1.20
75 Gemini 3.6 Flash (high reasoning)Google
53.4%
$1.50 / $7.50
75 MiniMax M3.1 FlashMiniMax
53.4%
$0.15 / $0.60
75 GPT-6.1 Terra (extra-high reasoning)OpenAI
53.4%
$1 / $5
78 Qwen3.8-Max (0803)Alibaba
53.2%
–
78 GPT-6.1 Sol (low reasoning)OpenAI
53.2%
$2 / $10
78 GPT-6.1 Sol (medium reasoning)OpenAI
53.2%
$2 / $10
81 Grok 4.6 (extra-high reasoning)xAI
53.0%
$2 / $6
82 Claude Sonnet 5.5 (medium reasoning)Anthropic
52.9%
$2 / $10
83 Kimi K3 (low reasoning)Moonshot AI
52.7%
$3 / $15
84 GPT-5.5 Instant (2026-06-26)OpenAI
52.5%
–
85 GPT-5.6 Terra (high reasoning)OpenAI
52.4%
$2 / $12
85 GPT-6.1 Terra (low reasoning)OpenAI
52.4%
$1 / $5
87 GPT-5.6 Terra (extra-high reasoning)OpenAI
52.3%
$2 / $12
88 Qwen3.8-Max (0902)Alibaba
52.1%
$2 / $6
88 GPT-5.4 mini (extra-high reasoning)OpenAI
52.1%
$0.75 / $4.50
90 DeepSeek-V4.1-Flash (max reasoning)DeepSeek
51.9%
$0.30 / $1.20
91 Claude Haiku 5.5 (extra-high reasoning)Anthropic
51.7%
$0.10 / $0.50
91 GPT-6 Luna (extra-high reasoning)OpenAI
51.7%
$0.10 / $0.50
93 Claude Sonnet 5 (medium reasoning)Anthropic
51.6%
$2 / $10
93 GPT-5.6 Luna (high reasoning)OpenAI
51.6%
$0.20 / $1.20
93 GPT-6.1 Terra (high reasoning)OpenAI
51.6%
$1 / $5
93 GPT-6.1 Terra (medium reasoning)OpenAI
51.6%
$1 / $5
93 GLM-5.3-FlashZ.ai
51.6%
$0.15 / $0.50
98 Claude Opus 5 (medium reasoning)Anthropic
51.5%
$5 / $25
98 Kimi K2.6Moonshot AI
51.5%
$0.95 / $4
100 MiMo-V2.6-FlashXiaomi
51.3%
$0.14 / $0.28
101 GLM-5.2 (max reasoning)Z.ai
51.2%
$1.40 / $4.40
102 DeepSeek-V4-Pro (0813, max reasoning)DeepSeek
51.0%
$1.32 / $3.96
103 GPT-6 Luna (medium reasoning)OpenAI
50.9%
$0.10 / $0.50
104 DeepSeek-V4-Pro (0423, max reasoning)DeepSeek
50.8%
$1.42 / $2.83
105 Qwen3.8-Flash-NextAlibaba
50.6%
–
105 MiMo-V2.5-Pro (reasoning on)Xiaomi
50.6%
$0.43 / $0.87
107 GPT-5.6 Luna (extra-high reasoning)OpenAI
50.5%
$0.20 / $1.20
107 GPT-5.6 Terra (medium reasoning)OpenAI
50.5%
$2 / $12
109 DeepSeek-V4-Flash (0731, max reasoning)DeepSeek
50.3%
$0.13 / $0.40
109 GPT-6 Luna (high reasoning)OpenAI
50.3%
$0.10 / $0.50
111 GPT-6 Sol (low reasoning)OpenAI
50.2%
$2 / $10
112 Claude Sonnet 4.6 (max reasoning)Anthropic
50.1%
$3 / $15
112 Claude Sonnet 5 (low reasoning)Anthropic
50.1%
$2 / $10
112 MiniMax-M2.7MiniMax
50.1%
$0.30 / $1.20
115 GPT-5.6 Terra (low reasoning)OpenAI
49.9%
$2 / $12
116 DeepSeek-V4-Flash-Vision-Exp (max reasoning)DeepSeek
49.7%
$0.22 / $0.65
116 Inkling SmallThinking Machines
49.7%
$0.45 / $1.20
118 Qwen3.7-MaxAlibaba
49.5%
$1.48 / $4.42
119 Grok 4.6 (low reasoning)xAI
49.4%
$2 / $6
120 Claude Haiku 5.5 (low reasoning)Anthropic
49.2%
$0.10 / $0.50
120 Claude Opus 5 (low reasoning)Anthropic
49.2%
$5 / $25
122 Claude Sonnet 5.5 (low reasoning)Anthropic
49.1%
$2 / $10
123 Claude Haiku 5.5 (medium reasoning)Anthropic
49.0%
$0.10 / $0.50
124 Claude Haiku 5.5 (high reasoning)Anthropic
48.7%
$0.10 / $0.50
125 Hy3Tencent
48.6%
$0.14 / $0.58
126 Beam 1.0 501B A23BReflection
48.5%
$0.40 / $1.20
127 Grok 4.3 (high reasoning)xAI
48.3%
$1.25 / $2.50
128 Solar Pro 4Upstage
48.0%
$0.15 / $0.60
129 Kimi K2.7 CodeMoonshot AI
47.8%
$0.95 / $4
129 Nemotron 3.5 Super VLNVIDIA
47.8%
$0.15 / $0.50
129 GPT-6.1 Terra (no reasoning)OpenAI
47.8%
$1 / $5
132 GPT-5.6 Sol (no reasoning)OpenAI
47.7%
$4 / $20
133 GPT-6 Sol (no reasoning)OpenAI
47.3%
$2 / $10
134 GPT-5.4 nano (extra-high reasoning)OpenAI
47.2%
$0.20 / $1.25
135 MiniMax-M3MiniMax
47.1%
$0.30 / $1.20
136 Inkling (extra-high reasoning)Thinking Machines
47.0%
$1 / $4.05
137 GPT-6 Luna (low reasoning)OpenAI
46.9%
$0.10 / $0.50
138 GPT-5.6 Luna (medium reasoning)OpenAI
46.8%
$0.20 / $1.20
139 Qwen3.8-27B (extra-high reasoning)Alibaba
46.6%
$0.50 / $3
140 Gemini 2.5 ProGoogle
46.3%
$1.25 / $10
141 Qwen3.7-PlusAlibaba
46.1%
$0.32 / $1.28
141 GPT-5.6 Luna (low reasoning)OpenAI
46.1%
$0.20 / $1.20
143 Claude Sonnet 4.5 (reasoning on)Anthropic
45.7%
$3 / $15
144 Gemma 4 31BGoogle
45.5%
$0.15 / $0.40
145 DeepSeek-V4-Flash (0423, max reasoning)DeepSeek
45.3%
$0.05 / $0.45
146 GPT-5.6 Terra (no reasoning)OpenAI
45.1%
$2 / $12
147 Muse Glimmer (high reasoning)Meta
44.9%
–
148 Qwen3.5-397B-A17BAlibaba
44.8%
$0.55 / $3.50
148 GLM-5.1Z.ai
44.8%
$1.33 / $4.18
150 MiMo-V2.5Xiaomi
43.9%
$0.40 / $2
151 Gemini 3.1 Flash-Lite PreviewGoogle
43.4%
$0.25 / $1.50
152 GPT-6 Luna (no reasoning)OpenAI
43.1%
$0.10 / $0.50
153 Qwen3.6-27BAlibaba
42.8%
$0.30 / $3.20
153 o3-mini (high reasoning)OpenAI
42.8%
–
155 Claude Haiku 4.5 (reasoning on)Anthropic
42.2%
$1 / $5
156 GLM-5.3 (low reasoning)Z.ai
42.0%
$1.40 / $4.40
157 Qwen3-235B-A22B-Thinking-2507Alibaba
41.4%
$0.45 / $3.50
158 Gemini 3.5 Flash-LiteGoogle
41.3%
$0.30 / $2.50
159 Trinity Large ThinkingArcee AI
40.6%
–
160 GPT-5.6 Luna (no reasoning)OpenAI
40.4%
$0.20 / $1.20
161 DeepSeek-V4-Flash (0423, high reasoning)DeepSeek
40.2%
$0.05 / $0.45
161 Mistral Medium 3.5Mistral AI
40.2%
$1.50 / $7.50
163 Qwen3.8-27B (low reasoning)Alibaba
40.0%
$0.50 / $3
163 Gemma 4 26B A4BGoogle
40.0%
$0.09 / $0.30
165 DeepSeek-V4-Pro (0813, no reasoning)DeepSeek
39.9%
$1.32 / $3.96
166 Qwen3.5-122B-A10BAlibaba
39.7%
$0.26 / $2.08
167 Grok 4.3 (no reasoning)xAI
39.4%
$1.25 / $2.50
168 Qwen3.8-27B (medium reasoning)Alibaba
39.0%
$0.50 / $3
168 DeepSeek-V3-0324DeepSeek
39.0%
$0.25 / $1
168 GPT-5 mini (high reasoning)OpenAI
39.0%
$0.25 / $2
171 gpt-oss-20b (high reasoning)OpenAI
38.9%
$0.03 / $0.14
172 Mistral Small 4Mistral AI
38.8%
$0.15 / $0.60
173 DeepSeek-V4.1-Flash-1017 (no reasoning)DeepSeek
38.5%
$0.30 / $1.20
174 DeepSeek-R1DeepSeek
38.3%
–
175 DeepSeek-V3.1-Terminus (reasoning on)DeepSeek
38.0%
$0.27 / $1
176 Mercury 2Inception
37.7%
–
177 Qwen3.6-35B-A3BAlibaba
36.6%
$0.10 / $0.95
177 Mistral Large 3Mistral AI
36.6%
$0.50 / $1.50
179 Qwen3.8-27B (no reasoning)Alibaba
36.2%
$0.50 / $3
179 Qwen3-Coder-NextAlibaba
36.2%
$0.12 / $0.80
179 Nemotron 3 Super 120B A12BNVIDIA
36.2%
$0.08 / $0.45
182 Qwen3-32B (reasoning on)Alibaba
36.0%
$0.14 / $0.40
183 DeepSeek-V3DeepSeek
35.8%
$0.26 / $1.03
184 DeepSeek-V4.1-Flash (no reasoning)DeepSeek
35.5%
$0.30 / $1.20
185 gpt-oss-120b (high reasoning)OpenAI
34.0%
$0.10 / $0.50
186 Qwen3-30B-A3B-Thinking-2507Alibaba
33.0%
–
187 Devstral 2Mistral AI
32.8%
$0.40 / $2
188 Devstral Small 2Mistral AI
32.4%
–
188 Mistral Medium 3.1Mistral AI
32.4%
$0.40 / $2
190 Llama 4 MaverickMeta
31.7%
$0.35 / $1
191 Granite 4.2 8BIBM
31.5%
$0.06 / $0.15
192 Qwen3-14B (reasoning on)Alibaba
30.7%
$0.10 / $0.22
193 Nemotron 3 Nano 30B A3B (reasoning on)NVIDIA
30.6%
$0.06 / $0.24
194 Qwen3.5-9BAlibaba
29.5%
$0.10 / $0.15
195 Mistral Small 3.2 24BMistral AI
28.6%
$0.094 / $0.25
196 Qwen3-8B (reasoning on)Alibaba
27.9%
–
197 Mistral Small 3.1 24BMistral AI
27.8%
$0.35 / $0.56
198 Solar Pro 3Upstage
25.5%
–
199 Gemma 4 E4BGoogle
24.4%
–
200 Ministral 3 14BMistral AI
23.8%
$0.20 / $0.20
201 Gemma 3 27BGoogle
23.3%
$0.08 / $0.35
202 Llama 4 ScoutMeta
21.3%
$0.10 / $0.30
203 Ministral 3 8BMistral AI
20.7%
$0.15 / $0.15
204 Gemma 3 12BGoogle
16.4%
$0.05 / $0.15
205 Ministral 3 3BMistral AI
15.3%
$0.10 / $0.10

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

SciCode, 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%20%40%60%80% 2025Jul2026Jul DeepSeek-V3DeepSeek-R1o3-miniGemini 2.5 ProClaude Sonnet 4.6Gemini 3.1 Pro PreviewClaude Fable 5Claude Fable 5.1Claude Opus 5.5

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; 14 others not drawn.

AnthropicGoogleXiaomiMoonshot AIMetaZ.ai

20%30%40%50%60%70% 2025Jul2026Jul AnthropicGoogleXiaomiMoonshot AIMetaZ.ai

What it measures

Share of scientific coding sub-problems solved, as run by Artificial Analysis with its own harness and prompts.

What it does not measure

Not general software engineering.

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.