AA score/cost comparison

Snapshot #2 fetched 2026-05-12 00:00:09 · 7.55 MB raw HTML · 516 models

Snapshot

Pick the stored fetch snapshot to compare.

Scoring

Choose the quality benchmark and final score formula.

Cost adjustment

Tune formulas that account for benchmark cost.

Result set

Control table filtering, ordering, and row count.

Top quality model in this view: GPT-5.5 (xhigh) (64.5 pts, $3,357) · sorted by score

Historic #1 winner?

Top row for each successful snapshot using the current mode/calc/cost settings and score sort.

Latest #1 GPT-5.5 (xhigh) 64.5
65.5 63.5 #1 · GPT-5.5 (xhigh) · score 64.5 · 2026-05-11 23:17:33#2 · GPT-5.5 (xhigh) · score 64.5 · 2026-05-12 00:00:09 GPT-5.5 (xhigh)

Recent winner changes

GPT-5.5 (xhigh) 2026-05-11 23:17:33 · 64.5
Run?Fetched?Winner?Score?Qual?Cost?
#2 2026-05-12 00:00:09 GPT-5.5 (xhigh) 64.5 64.5 $3,357
#1 2026-05-11 23:17:33 GPT-5.5 (xhigh) 64.5 64.5 $3,357
#?Pareto?Model?Released?Cost$?$/Q?Qual?ΔTop?Intel?Code?Agent?Pen?Score?
1 ✓ GPT-5.5 (xhigh)
OpenAI		 2026-04-23 $3,357 52.05 64.5 0.0 60.2 59.1 74.1 35.3 64.5
2 ✓ GPT-5.5 (high)
OpenAI		 2026-04-23 $2,159 34.21 63.1 -1.4 58.9 58.5 72.0 33.3 63.1
3 ✓ GPT-5.5 (medium)
OpenAI		 2026-04-23 $1,199 19.73 60.8 -3.7 56.7 56.2 69.4 30.8 60.8
4 ✓ Gemini 3.1 Pro Preview
Google		 2026-02-19 $892 15.58 57.3 -7.2 57.2 55.5 59.1 29.5 57.3
5 ✓ MiMo-V2.5-Pro
Xiaomi		 2026-04-22 $462 8.30 55.6 -8.9 53.8 45.5 67.4 26.6 55.6
6 ✓ Grok 4.3
xAI		 2026-04-30 $395 7.40 53.4 -11.1 53.2 41.0 65.9 26.0 53.4
7 ✓ MiMo-V2.5
Xiaomi		 2026-04-22 $207 3.97 52.2 -12.3 49.0 42.1 65.5 23.2 52.2
8 ✓ MiniMax-M2.7
MiniMax		 2026-03-18 $176 3.44 51.0 -13.5 49.6 41.9 61.5 22.4 51.0
9 ✓ DeepSeek V4 Flash (Reasoning, Max Effort)
DeepSeek		 2026-04-24 $113 2.31 48.8 -15.7 46.5 38.7 61.3 20.5 48.8
10 ✓ DeepSeek V4 Flash (Reasoning, High Effort)
DeepSeek		 2026-04-24 $57.2 1.20 47.5 -17.0 44.9 39.8 57.8 17.6 47.5
11 ✓ DeepSeek V4 Flash (Non-reasoning)
DeepSeek		 2026-04-24 $40.0 0.90 44.3 -20.2 36.5 35.1 61.3 16.0 44.3
12 ✓ Grok 4.1 Fast (Reasoning)
xAI		 2025-11-19 $39.6 1.00 39.6 -24.9 38.6 30.9 49.3 16.0 39.6
13 ✓ MiMo-V2-Flash (Non-reasoning)
Xiaomi		 2025-12-16 $21.4 0.62 34.5 -30.0 30.4 25.8 47.3 13.3 34.5
14 ✓ Grok 4.1 Fast (Non-reasoning)
xAI		 2025-11-19 $21.4 0.84 25.3 -39.2 23.6 19.5 33.0 13.3 25.3
15 ✓ Grok 4 Fast (Non-reasoning)
xAI		 2025-09-19 $17.4 0.71 24.7 -39.8 23.1 19.0 31.9 12.4 24.7
16 ✓ gpt-oss-120B (low)
OpenAI		 2025-08-05 $15.9 0.70 22.7 -41.8 24.5 15.5 28.0 12.0 22.7
17 ✓ gpt-oss-20B (low)
OpenAI		 2025-08-05 $7.68 0.40 19.0 -45.5 20.8 14.4 21.9 8.9 19.0
18 ✓ Qwen3.5 0.8B (Non-reasoning)
Alibaba		 2026-03-02 $6.67 0.61 10.9 -53.6 9.9 1.0 21.7 8.2 10.9
19 ✓ Granite 4.0 H Small
IBM		 2025-09-22 $4.48 0.54 8.4 -56.1 10.8 8.5 5.8 6.5 8.4
20 ✓ Phi-4
Microsoft		 2024-12-12 $4.27 0.59 7.2 -57.3 10.4 11.2 0.0 6.3 7.2
21 ✓ Apertus 70B Instruct
Swiss AI Initiative		 2025-09-02 $3.78 0.82 4.6 -59.9 7.7 1.9 4.3 5.8 4.6
22 ✓ Apertus 8B Instruct
Swiss AI Initiative		 2025-09-02 $0.10 0.03 3.7 -60.8 5.9 1.4 3.8 0.0 3.7