SciCode

Artificial Analysis · 50 models

Rank	Model	Score
1	Claude Opus 5.5 (Max, Default Fallback)	0.669
2	Claude Opus 5.5 (Xhigh, Default Fallback)	0.65
3	Claude Fable 5.1 (Max, Default Fallback)	0.631
4	Muse Wonder Full (Max)	0.626
5	Gemini 4 Argon (High)	0.618
6	Claude Fable 5 (Max, Opus 4.8 Fallback)	0.61
6	Claude Sonnet 5.5 (Max, Default Fallback)	0.61
8	Claude Fable 5.1 (Xhigh, Default Fallback)	0.609
8	MiMo-V2.6-Pro	0.609
10	Kimi K3.1 Pro	0.608
11	Claude Opus 5.5 (High, Default Fallback)	0.604
12	Muse Wonder (Max)	0.603
13	Gemini 3.7 Flash (Medium)	0.598
14	Muse Spark 1.3 (Xhigh)	0.597
15	Kimi K3 (Max)	0.595
16	Claude Opus 5.5 (Medium, Default Fallback)	0.593
17	GLM-5.3 (Max)	0.59
18	Step 5 Preview	0.589
19	Muse Spark 1.1 (Xhigh)	0.588
19	Muse Spark 1.3 (Max)	0.588
21	Claude Fable 5.1 (High, Default Fallback)	0.587
21	Gemini 3.1 Pro Preview	0.587
23	Claude Opus 5.5 (Low, Default Fallback)	0.586
24	Muse Spark Open (Xhigh)	0.584
25	GPT-5.6 Sol (High)	0.578
25	Grok 4.7 (High)	0.578
27	GPT-6 Sol (Max)	0.576
28	GPT-5.6 Sol (Medium)	0.574
28	Grok 4.7 (Xhigh)	0.574
28	Muse Spark 1.2 (Xhigh)	0.574
31	Claude Sonnet 5.5 (Xhigh, Default Fallback)	0.573
32	Gemini 3.7 Flash (High)	0.572
33	GPT-5.6 Sol (Max)	0.571
33	GPT-5.6 Sol (Xhigh)	0.571
35	Ling 3.1 Flash 1019	0.568
36	Claude Fable 5.1 (Low, Default Fallback)	0.567
37	Gemini 3.8 Flash (High)	0.566
38	GPT-6 Astra (Max)	0.565
38	Grok 4.6 (High)	0.565
40	Claude Fable 5.1 (Medium, Default Fallback)	0.564
40	Claude Opus 5 (Max)	0.564
40	GPT-5.6 Sol (Low)	0.564
43	GPT-5.5 (High)	0.561
44	DeepSeek V4.1 Flash 1017 (Max)	0.559
44	Grok 4.6 (Medium)	0.559
46	GPT-5.5 (Xhigh)	0.558
46	GPT-6.1 Sol (High)	0.558
48	Claude Opus 5 (Xhigh)	0.557
48	GPT-6 Astra (Xhigh)	0.557
48	GPT-6.1 Sol (Xhigh)	0.557