Cookies on AIGROW

We use necessary cookies to run the site. With your permission, we also use cookies for analytics, session recordings and marketing attribution.

Cookie Policy

AI leaderboard · Factual answers

AI factual accuracy benchmark: 94 models ranked on measured results

SimpleQA Verified: 1,000 short questions on politics, science, art, sports, places, music and more, each with one right answer. The score is the share answered correctly. Epoch AI runs it.

Run Claude Fable 5.2 up to 60% below list price. $25 a month brings $110 of API credit and cancels any time; $25 once buys $100. Results from tests Epoch AI runs, data of 12 November 2026, under CC BY 4.0. Prices from each maker’s pricing page, read on 12 November 2026.

Top score
94.0%Claude Fable 5.2 from Anthropic
Models ranked
94
Level with the leader
0
On sale with AIGROW credit
9
Data of
12 November 2026

Level: its interval overlaps the leader’s.

On SimpleQA Verified, run by Epoch AI, Claude Fable 5.2 from Anthropic leads 94 models with 94.0% of the questions answered correctly (data of 12 November 2026). No other model is statistically level with it. AIGROW API credit sells it at $3.20 / $16.00 instead of $8.00 / $40.00 per million input / output tokens.

Run models from this ranking below list price

AIGROW API credit runs these models through one key, billed per token at the rates below. $25 a month brings $110 of API credit and cancels any time; $25 once buys $100.

  1. No. 1Claude Fable 5.2AnthropicList price $8.00 / $40.00$3.20 / $16.00with AIGROW API creditRun Claude Fable 5.2 up to 60% below list priceCertified genuine by AIGROW on 11 November 2026
  2. No. 3Gemini 4 ArgonGoogleList price $2.00 / $10.00$1.00 / $5.00with AIGROW API creditRun Gemini 4 Argon up to 50% below list priceCertified genuine by AIGROW on 11 November 2026
  3. No. 4GPT-6 AstraOpenAIList price $10.00 / $50.00$2.50 / $12.50with AIGROW API creditRun GPT-6 Astra up to 75% below list priceCertified genuine by AIGROW on 11 November 2026

US dollars per million input / output tokens. Certified genuine by AIGROW means the model passed AIGROW’s own check against the same model at its maker on 11 November 2026. No model maker reviewed or endorsed it.

AI factual accuracy benchmark

It tests recall of short facts, not long answers or sources, and the models are told to guess rather than say they do not know.

Results of 94 AI models on SimpleQA Verified, with their 95% intervals and list prices
#ModelScoreSetting and runLMArena factualityPer 1M tokens, in / out
1Claude Fable 5.2AnthropicRun Claude Fable 5.2 up to 60% below list priceCertified genuine by AIGROW on 11 November 202694.0%95% interval 92.5% to 95.5%max, run 6 Nov 2026Not on the boardList price $8.00 / $40.00$3.20 / $16.00with AIGROW API credit
2Gemini 4 CarbonGoogle DeepMind77.7%95% interval 75.1% to 80.3%high, run 2 Nov 2026152195% interval 1513 to 1530$2.00 / $10.00
3Gemini 4 ArgonGoogle DeepMindRun Gemini 4 Argon up to 50% below list priceCertified genuine by AIGROW on 11 November 202676.0%95% interval 73.4% to 78.6%Its interval overlaps 1 model above ithigh, run 13 Oct 2026149895% interval 1493 to 1503List price $2.00 / $10.00$1.00 / $5.00with AIGROW API credit
4GPT-6 AstraOpenAIRun GPT-6 Astra up to 75% below list priceCertified genuine by AIGROW on 11 November 202675.6%95% interval 72.9% to 78.3%Its interval overlaps 2 models above itmax, run 30 Aug 2026146695% interval 1461 to 1470List price $10.00 / $50.00$2.50 / $12.50with AIGROW API credit
5GPT-6.1 SolOpenAIRun GPT-6.1 Sol up to 75% below list priceCertified genuine by AIGROW on 11 November 202673.9%95% interval 71.2% to 76.6%Its interval overlaps 3 models above itmax, run 29 Sept 2026146795% interval 1462 to 1473List price $2.00 / $10.00$0.50 / $2.50with AIGROW API credit
6Gemini 3.1 Pro (preview)Google DeepMind73.5%95% interval 70.8% to 76.2%Its interval overlaps 4 models above ithigh, run 10 Aug 2026147195% interval 1469 to 1474$2.00 / $12.00
7Claude Opus 5.5AnthropicRun Claude Opus 5.5 up to 60% below list priceCertified genuine by AIGROW on 11 November 202672.2%95% interval 69.4% to 75.0%Its interval overlaps 4 models above itmax, run 22 Sept 2026150695% interval 1500 to 1511List price $4.00 / $20.00$1.60 / $8.00with AIGROW API credit
8Claude Fable 5.1AnthropicRun Claude Fable 5.1 up to 60% below list priceCertified genuine by AIGROW on 11 November 202670.8%95% interval 68.0% to 73.6%Its interval overlaps 5 models above itmax, run 1 Sept 2026149995% interval 1494 to 1504List price $10.00 / $50.00$4.00 / $20.00with AIGROW API credit
9Claude Fable 5Anthropic70.7%95% interval 67.9% to 73.5%Its interval overlaps 6 models above itxhigh, run 10 Aug 2026Not on the boardNo list price
10Gemini 3.8 FlashGoogle DeepMind69.7%95% interval 66.9% to 72.5%Its interval overlaps 5 models above ithigh, run 2 Sept 2026147195% interval 1467 to 1474$0.75 / $3.75
11GPT-5.6 SolOpenAI69.7%95% interval 66.9% to 72.5%Its interval overlaps 6 models above itmax, run 10 Aug 2026147695% interval 1473 to 1479$4.00 / $20.00
12Gemini 3.7 FlashGoogle DeepMind69.2%95% interval 66.3% to 72.1%Its interval overlaps 7 models above ithigh, run 27 Aug 2026Not on the boardNo list price
13Gemini 3 FlashGoogle DeepMind66.8%95% interval 63.9% to 69.7%Its interval overlaps 6 models above ithigh, run 27 Aug 2026Not on the board$0.50 / $3.00
14Gemini 3.5 FlashGoogle DeepMind66.2%95% interval 63.3% to 69.1%Its interval overlaps 6 models above ithigh, run 27 Aug 2026Not on the boardNo list price
15Gemini 3.6 FlashGoogle DeepMind66.2%95% interval 63.3% to 69.1%Its interval overlaps 7 models above ithigh, run 27 Aug 2026Not on the boardNo list price
16GPT-5.5OpenAI63.0%95% interval 60.0% to 66.0%Its interval overlaps 3 models above itxhigh, run 27 Aug 2026148595% interval 1483 to 1488$5.00 / $30.00
17Kimi K3.1 ProMoonshot62.2%95% interval 59.2% to 65.2%Its interval overlaps 4 models above itmax, run 6 Nov 2026147695% interval 1467 to 1485$2.00 / $10.00
18GPT-6 SolOpenAI60.7%95% interval 57.7% to 63.7%Its interval overlaps 4 models above itmax, run 22 Sept 2026143995% interval 1434 to 1444$2.00 / $10.00
19Muse Spark 1.2Meta AI60.3%95% interval 57.3% to 63.3%Its interval overlaps 5 models above itxhigh, run 27 Aug 2026Not on the boardNo list price
20Claude Opus 5Anthropic59.9%95% interval 56.9% to 62.9%Its interval overlaps 4 models above itmax, run 10 Aug 2026148895% interval 1484 to 1491$5.00 / $25.00
21Muse Spark 1.1Meta AI57.8%95% interval 54.7% to 60.9%Its interval overlaps 5 models above itRun 31 Aug 2026Not on the boardNo list price
22GPT-6.1 TerraOpenAIRun GPT-6.1 Terra up to 75% below list priceCertified genuine by AIGROW on 11 November 202657.3%95% interval 54.2% to 60.4%Its interval overlaps 6 models above itmax, run 26 Oct 2026Not on the boardList price $1.00 / $5.00$0.25 / $1.25with AIGROW API credit
23Muse Spark OpenMeta AI56.6%95% interval 53.5% to 59.7%Its interval overlaps 6 models above itxhigh, run 15 Oct 2026Not on the boardNo list price
24Grok 4.7xAIRun Grok 4.7 up to 75% below list priceCertified genuine by AIGROW on 11 November 202656.0%95% interval 52.9% to 59.1%Its interval overlaps 6 models above itxhigh, run 22 Sept 2026143795% interval 1432 to 1441List price $2.00 / $6.00$0.50 / $1.50with AIGROW API credit
25Qwen3.7-MaxAlibaba55.8%95% interval 52.7% to 58.8%Its interval overlaps 7 models above itRun 27 Aug 2026Not on the boardNo list price

How to read this ranking

What the scores measure, what they leave out, and where each number comes from.

What it measures
SimpleQA Verified: 1,000 short questions on politics, science, art, sports, places, music and more, each with one right answer. The score is the share answered correctly. Epoch AI runs it.
What it leaves out
It tests recall of short facts, not long answers or sources, and the models are told to guess rather than say they do not know.
How to read the margin
Each result carries a 95% interval, 1.96 standard errors either side as Epoch AI publishes them; an average combines the errors of its tests. Where two intervals overlap, the tests cannot say which model is better. Rows are still numbered by score, and a row says how many models above it overlap.
Settings
Under each result is the reasoning setting Epoch AI ran the model at, as it names it, and the day of the run. Where a model ran at several settings, the best result counts.
The second column
LMArena’s factuality board blends its blind votes with checks of the facts in each answer: claims are pulled from the answers and checked by search agents, and by default the checks weigh 25% of the score. It is shown beside the test, not used to rank.
Not updated in over 120 days
A result run more than 120 days before the newest data on these pages carries this mark, so an older result can be weighed as one.
Prices
The list price per million tokens from the maker’s own pricing page, read on 12 November 2026. It is a price per token, not per answer: a higher reasoning setting spends more tokens on the same question. Where AIGROW API credit sells a model, the list price is struck through and the price through the credit sits under it.

Source: Epoch AI, SimpleQA Verified (data of 12 November 2026), licensed under CC BY 4.0; LMArena, leaderboard dataset (revision 4217986c, published 9 November 2026), licensed under CC BY 4.0. We change no score: we add the prices and the links to our model pages.

What each of them costs to run

The price list works three everyday jobs on every model, and our own benchmark runs them on real business tasks to see which pass.

See the pricesSee the benchmark

Data of 12 November 2026