Skip to content
AI Tracker

Price per IQ

What a fixed level of capability costs, and how fast that price falls.

8 entries · 3 charts1 updated Follow (RSS)

Progress over time

All metrics →

Cost per task for 75%+ on ARC-AGI-1 puzzles

$0.012

3 mo agoDeepSeek V4 Flash (low)Jul 2026

  1. 6 mo$0.17Gemini 3 Flash Preview (high)15× cheaper
  2. 1 yr$8.42Grok 4 refinement system714× cheaper
  3. 2 yrno result yet
  4. 3 yrno result yet

Charts

Price of GPT-4-level performance

Cheapest non-reasoning model scoring at least GPT-4's level (≥33% on GPQA Diamond), USD per million tokens (3:1 input:output blend). Log scale.

What this measures: What it costs to use an AI at least as capable as the original GPT-4 (2023). A million tokens is roughly 750,000 words of input and output.

$0.01$0.10$1$10$100202420252026

2023–2024 points are Epoch AI's. Points from late 2024 on are AI Tracker's extension using archived OpenRouter price lists and published GPQA Diamond scores (one provider route, not always the cheapest). The price of this capability level has flattened at roughly $0.05–0.13 since late 2024; the steep declines are now at higher capability levels (see the ARC-AGI cost chart). Per-token price is not cost per task.

Sources: Epoch AI, OpenRouter via Internet Archive, Google DeepMindData as of 9 Nov 2026
Show data table and sources
DateLabelValue
14 Mar 2023GPT-4$37.50
6 Nov 2023GPT-4 Turbo$15
26 Feb 2024Mistral Large$6
4 Mar 2024Claude 3 Haiku$0.50
4 Nov 2024Gemini 1.5 Flash$0.13
13 Dec 2024Phi 4$0.12
3 May 2025Gemma 3 12B$0.063
1 Nov 2025Gemma 3 12B$0.048
4 May 2026Mistral Small 3$0.058
1 Nov 2026Mistral Small 3$0.058

Cost per task to score 75%+ on ARC-AGI-1

Cheapest entry on ARC Prize's leaderboard scoring at least 75% on the ARC-AGI-1 semi-private set, USD per task. Log scale.

What this measures: How much it costs an AI to solve one ARC-AGI-1 visual logic puzzle while scoring 75% or more.

$0.01$0.10$1$10$100$1,00020252026

Dates are ARC Prize's model release dates. Costs depend on ARC Prize's pricing assumptions, which it has revised (o3-preview went from $26 to $200 per task). The tested o3-preview was trained on part of the public training set and differs from the released o3.

Source: ARC PrizeData as of 9 Nov 2026
Show data table and sources
DateLabelValue
20 Dec 2024o3-preview (low)$200
7 Aug 2025Grok 4 refinement system$8.42
18 Nov 2025Gemini 3 Pro$0.49
17 Dec 2025Gemini 3 Flash Preview (high)$0.17
9 Jul 2026GPT-5.6 Terra (medium)$0.13
21 Jul 2026Gemini 3.6 Flash (low)$0.12
30 Jul 2026GPT-5.6 Luna (high)$0.028
31 Jul 2026DeepSeek V4 Flash (low)$0.012

Top AI score on an offline IQ-style test

Best monthly score on TrackingAI's verbal IQ-style quiz that has never been published online. Human average = 100.

What this measures: A short IQ-style pattern quiz that has never been published online, so models can't have memorised it. 100 is the human average.

  • Top model (offline test)
  • Reference level
709011013015020252026Human average (100)

Monthly maxima, dated to the end of each month. IQ norms are designed for humans and aren't validated for AI; this is a small matrix-style quiz, not a measure of general intelligence. On the public Mensa Norway test (which may be in training data) scores are higher, about 150.

Source: TrackingAIData as of 9 Nov 2026
Show data table and sources
DateLabelValue
31 May 2024Claude 385.5 points
30 Nov 2024o196.5 points
30 Nov 2025Grok 4123 points
31 May 2026GPT-5 Pro127 points
31 Oct 2026GPT Astra Ultra (TrackingAI label)136 points
Human average (100)100 points

Entries