Empirical evaluations measuring coding proficiency, reasoning benchmarks (GPQA, SWE-bench Verified, HLE), and real-time value-for-money ($/point) metrics.
Highlights
Updated Daily • Empirical Telemetry
Intelligence
Updated
Artificial Analysis Intelligence Index • Higher is better
GPT-6 Astra (max) Benchmarks, Price & Specs (Oct 2026): 55 (OpenAI)
55
O
GPT-6 Astra (m..
Claude Fable 5.1 (max with fallback): 53 (Anthropic)
53
A
Claude Fable 5..
Claude Opus 5 (max) Benchmarks, Price & Specs (Oct 2026): 53 (Anthropic)
53
A
Claude Opus 5 ..
Muse Spark 1.3 (max): 48 (Meta)
48
M
Muse Spark 1.3..
GPT-5.6 Sol (max) Benchmarks, Price & Specs (Oct 2026): 48 (OpenAI)
48
O
GPT-5.6 Sol (m..
GLM-5.3 (max): 45 (Z AI)
45
Z
GLM-5.3 (max)
Qwen3.8 Max (0902): 45 (Alibaba)
45
Q
Qwen3.8 Max (0..
Step 5 Preview: 44 (StepFun)
44
S
Step 5 Preview
Grok 4.6 (high): 44 (SpaceXAI)
44
X
Grok 4.6 (high)
Kimi K3 (max): 44 (Kimi)
44
K
Kimi K3 (max)
Speed
Output tokens per second • Higher is better
Gemini 3.5 Flash-Lite: 358 t/s (Google)
358 t/s
G
Gemini 3.5 Fla..
Gemini 3.8 Flash (high): 298 t/s (Google)
298 t/s
G
Gemini 3.8 Fla..
Muse Spark 1.3 (max): 214 t/s (Meta)
214 t/s
M
Muse Spark 1.3..
DeepSeek V4 Flash Vision (max): 214 t/s (DeepSeek)
214 t/s
D
DeepSeek V4 Fl..
DeepSeek V4.1 Flash (max): 208 t/s (DeepSeek)
208 t/s
D
DeepSeek V4.1 ..
MiniMax-M3: 186 t/s (MiniMax)
186 t/s
M
MiniMax-M3
gpt-oss-120b (high): 181 t/s (OpenAI)
181 t/s
O
gpt-oss-120b (..
Nemotron 3 Ultra: 164 t/s (NVIDIA)
164 t/s
N
Nemotron 3 Ultra
Mistral Medium 3.5: 137 t/s (Mistral)
137 t/s
M
Mistral Medium..
GPT-5.6 Luna (max): 133 t/s (OpenAI)
133 t/s
O
GPT-5.6 Luna (..
Cost per 1M Tokens
Weighted average blended price (USD) • Lower is better
Muse Glimmer (high): $0.12 (Meta)
$0.12
M
Muse Glimmer (..
Gemini 3.5 Flash-Lite: $0.18 (Google)
$0.18
G
Gemini 3.5 Fla..
gpt-oss-120b (high): $0.18 (OpenAI)
$0.18
O
gpt-oss-120b (..
GLM-5.3-Flash: $0.35 (Z AI)
$0.35
Z
GLM-5.3-Flash
DeepSeek V4.1 Flash (max): $0.37 (DeepSeek)
$0.37
D
DeepSeek V4.1 ..
Qwen3.8-Flash-Next: $0.45 (Alibaba)
$0.45
Q
Qwen3.8-Flash-..
DeepSeek V4 Flash Vision (max): $0.47 (DeepSeek)
$0.47
D
DeepSeek V4 Fl..
GPT-5.6 Luna (max): $0.52 (OpenAI)
$0.52
O
GPT-5.6 Luna (..
Mistral Medium 3.5: $0.60 (Mistral)
$0.60
M
Mistral Medium..
MiniMax-M3: $0.60 (MiniMax)
$0.60
M
MiniMax-M3
Artificial Analysis Intelligence Index #
↗ Intelligence Index v4.3 incorporates evaluations: SWE-bench Verified (40%), Terminal-Bench 2.0 (25%), Aider Polyglot (20%), LiveCodeBench (15%). Every figure is verified against primary source logs without prompt leakage.
Intelligence Index vs. Cost per 1M Tokens
Code Intelligence Index vs. Weighted average cost (USD, Log Scale)
Frontier Language Model Intelligence, Over Time
Progressive evolution across Anthropic, OpenAI, DeepSeek, Google, and Meta from 2023 to 2026.
Canonical Benchmark Suite
Breakdown across isolated execution harnesses matching Artificial Analysis methodologies.
Value-for-Money Intelligence vs. Cost Matrix
| RANK | MODEL & CREATOR | |||||||
|---|---|---|---|---|---|---|---|---|
| 01 | Claude Fable 5.1 (max with fallback) Anthropic • API • ▲ +1 | —% | —% | 1M | 68 t/s TTFT: 262210ms | $30.0000 | — | |
| 02 | Muse Spark 1.3 (max) Meta • API • ▲ +1 | —% | —% | 1M | 214 t/s TTFT: 24160ms | $2.2500 | — | |
| 03 | GLM-5.3 (max) Z AI • API • ▲ +1 | —% | —% | 1M | 72 t/s TTFT: 2960ms | $1.5000 | — | |
| 04 | Qwen3.8 Max (0902) Alibaba • API • ▲ +1 | —% | —% | 984K | 37 t/s TTFT: 2720ms | $3.0000 | — | |
| 05 | Step 5 Preview StepFun • API • ▲ +1 | —% | —% | 1M | 100 t/s TTFT: 2960ms | $1.2000 | — | |
| 06 | Grok 4.6 (high) SpaceXAI • API • ▲ +1 | —% | —% | 500K | 60 t/s TTFT: 44250ms | $4.0000 | — | |
| 07 | Kimi K3 (max) Kimi • API • ▲ +1 | —% | —% | 1.05M | 38 t/s TTFT: 3990ms | $1.8000 | — | |
| 08 | GPT-5.6 Terra (max) OpenAI • API • ▲ +1 | —% | —% | 1M | 84 t/s TTFT: 220860ms | $3.1500 | — | |
| 09 | GLM-5.3-Flash Z AI • API • ▲ +1 | —% | —% | 1M | 95 t/s TTFT: 2500ms | $0.3500 | — | |
| 10 | Gemini 3.8 Flash (high) Google • API • ▲ +1 | —% | —% | 1M | 298 t/s TTFT: 15470ms | $1.3100 | — | |
| 11 | DeepSeek V4.1 Flash (max) DeepSeek • API • ▲ +1 | —% | —% | 1M | 208 t/s TTFT: 1140ms | $0.3700 | — | |
| 12 | Qwen3.8-Flash-Next Alibaba • API • ▲ +1 | —% | —% | 256K | 55 t/s TTFT: 2890ms | $0.4500 | — | |
| 13 | Qwen3.8 2.4T A95B Alibaba • API • ▲ +1 | —% | —% | 984K | 38 t/s TTFT: 2690ms | $2.2500 | — | |
| 14 | Claude Sonnet 5 (max) Anthropic • API • ▲ +1 | —% | —% | 1M | 74 t/s TTFT: 133400ms | $8.0000 | — | |
| 15 | GPT-5.6 Luna (max) OpenAI • API • ▲ +1 | —% | —% | 1M | 133 t/s TTFT: 113240ms | $0.5200 | — | |
| 16 | DeepSeek V4 Flash Vision (max) DeepSeek • API • ▲ +1 | —% | —% | 1M | 214 t/s TTFT: 1050ms | $0.4700 | — | |
| 17 | Qwen3.8 27B (xhigh) Alibaba • API • ▲ +1 | —% | —% | 256K | 43 t/s TTFT: 3840ms | $0.9000 | — | |
| 18 | Nemotron 3 Ultra NVIDIA • API • ▲ +1 | —% | —% | 262K | 164 t/s TTFT: 2400ms | $0.7500 | — | |
| 19 | gpt-oss-120b (high) OpenAI • API • ▲ +1 | —% | —% | 131K | 181 t/s TTFT: 850ms | $0.1800 | — | |
| 20 | Mistral Medium 3.5 Mistral • API • ▼ -1 | —% | —% | 256K | 137 t/s TTFT: 2290ms | $0.6000 | — | |
| 21 | Muse Glimmer (high) Meta • API • ▼ -2 | —% | —% | 131K | 93 t/s TTFT: 990ms | $0.1200 | — | |
| 22 | Gemini 3.5 Flash-Lite Google • API • ▼ -3 | —% | —% | 1M | 358 t/s TTFT: 9780ms | $0.1750 | — | |
| 23 | Inkling Thinking Machines • API • ▼ -5 | —% | —% | 1M | 81 t/s TTFT: 2480ms | $0.7500 | — | |
| 24 | Gemini 3.1 Pro Benchmarks, Price & Specs (Oct 2026) Google • API • ▲ +1 | —% | —% | 1M | 119 t/s TTFT: 33160ms | $1.4000 | — | |
| 25 | MiniMax-M3 MiniMax • API • ▼ -7 | —% | —% | 1M | 186 t/s TTFT: 1000ms | $0.6000 | — | |
| 26 | K2 Horizon 375B A23B Institute of Foundation Models • API • ▼ -8 | —% | —% | 524K | 80 t/s TTFT: 3500ms | $1.2000 | — | |
| 27 | DeepSeek V4 Pro Benchmarks, Price & Specs (Oct 2026) DeepSeek • API • ▼ -11 | —% | —% | 1M | 88 t/s TTFT: 1700ms | $0.9600 | — | |
| 28 | GPT-5.6 Sol (max) Benchmarks, Price & Specs (Oct 2026) OpenAI • API • ▼ -25 | —% | —% | 1M | 61 t/s TTFT: 129500ms | $6.1250 | — | |
| 29 | Claude Opus 5 (max) Benchmarks, Price & Specs (Oct 2026) Anthropic • API • ▲ +1 | —% | —% | 1M | 51 t/s TTFT: 57030ms | $20.0000 | — | |
| 30 | GPT-6 Astra (max) Benchmarks, Price & Specs (Oct 2026) OpenAI • API • ▼ -29 | —% | —% | 1M | 57 t/s TTFT: 283660ms | $12.0000 | — |
53.1%
—%
—%
1M
68 t/s (262210ms)
$30.0000
—
48.0%
—%
—%
1M
214 t/s (24160ms)
$2.2500
—
45.1%
—%
—%
1M
72 t/s (2960ms)
$1.5000
—
45.0%
—%
—%
984K
37 t/s (2720ms)
$3.0000
—
44.1%
—%
—%
1M
100 t/s (2960ms)
$1.2000
—
44.0%
—%
—%
500K
60 t/s (44250ms)
$4.0000
—
44.0%
—%
—%
1.05M
38 t/s (3990ms)
$1.8000
—
42.1%
—%
—%
1M
84 t/s (220860ms)
$3.1500
—
42.1%
—%
—%
1M
95 t/s (2500ms)
$0.3500
—
41.0%
—%
—%
1M
298 t/s (15470ms)
$1.3100
—
40.0%
—%
—%
1M
208 t/s (1140ms)
$0.3700
—
40.0%
—%
—%
256K
55 t/s (2890ms)
$0.4500
—
40.0%
—%
—%
984K
38 t/s (2690ms)
$2.2500
—
38.1%
—%
—%
1M
74 t/s (133400ms)
$8.0000
—
38.0%
—%
—%
1M
133 t/s (113240ms)
$0.5200
—
35.0%
—%
—%
1M
214 t/s (1050ms)
$0.4700
—
34.0%
—%
—%
256K
43 t/s (3840ms)
$0.9000
—
23.0%
—%
—%
262K
164 t/s (2400ms)
$0.7500
—
0.0%
—%
—%
131K
181 t/s (850ms)
$0.1800
—
0.0%
—%
—%
256K
137 t/s (2290ms)
$0.6000
—
0.0%
—%
—%
131K
93 t/s (990ms)
$0.1200
—
0.0%
—%
—%
1M
358 t/s (9780ms)
$0.1750
—
0.0%
—%
—%
1M
81 t/s (2480ms)
$0.7500
—
0.0%
—%
—%
1M
119 t/s (33160ms)
$1.4000
—
0.0%
—%
—%
1M
186 t/s (1000ms)
$0.6000
—
0.0%
—%
—%
524K
80 t/s (3500ms)
$1.2000
—
0.0%
—%
—%
1M
88 t/s (1700ms)
$0.9600
—
0.0%
—%
—%
1M
61 t/s (129500ms)
$6.1250
—
0.0%
—%
—%
1M
51 t/s (57030ms)
$20.0000
—
0.0%
—%
—%
1M
57 t/s (283660ms)
$12.0000
—