Comparisons
Every comparison table on this site is built from a shared set of figures rather than typed into each article. That means a correction lands everywhere the set is used, and every option carries the date it was last checked rather than an unstated assumption that it is current.
This page lists what exists.
The two structures, side by side
What happens to you if you are wrong?
| Set | aschenbrenner-buffett-structures |
|---|---|
| Options | 2, across 6 attributes |
| Last checked | 2026-07-31 |
| Used by | Leopold Aschenbrenner vs Buffett: Conviction vs Margin of Safety |
Anthropic's two nearest models
Which Anthropic model belongs in this comparison?
| Set | deepseek-v4-anthropic-bracket |
|---|---|
| Options | 2, across 4 attributes |
| Last checked | 2026-08-26 |
| Used by | DeepSeek V4 Flash vs Gemini, GPT and Claude: Similar AI Scores, Vastly Different Token Prices |
Gap is against DeepSeek V4 Flash at 52. Prices from Anthropic's pricing page, scores from each model's own page under Intelligence Index v4.1.1, both read 26 August 2026.
Intelligence Index scores
Which models is it actually competing with?
| Set | deepseek-v4-intelligence-index |
|---|---|
| Options | 5, across 2 attributes |
| Last checked | 2026-08-26 |
| Used by | DeepSeek V4 Flash vs Gemini, GPT and Claude: Similar AI Scores, Vastly Different Token Prices |
Read on each model's own page on 26 August 2026, under Intelligence Index v4.1.1.
Peer pricing at matched capability
At matched capability, what does each one cost?
| Set | deepseek-v4-peer-pricing |
|---|---|
| Options | 5, across 4 attributes |
| Last checked | 2026-08-26 |
| Used by | DeepSeek V4 Flash vs Gemini, GPT and Claude: Similar AI Scores, Vastly Different Token Prices |
Price multiples vs DeepSeek V4 Flash, off-peak
As multiples of DeepSeek V4 Flash's off-peak rates, what do the peers cost?
| Set | deepseek-v4-price-multiples |
|---|---|
| Options | 4, across 4 attributes |
| Last checked | 2026-08-26 |
| Used by | DeepSeek V4 Flash vs Gemini, GPT and Claude: Similar AI Scores, Vastly Different Token Prices |
Claude Fable 5 vs GPT-5.6 (Sol tier)
How does Claude Fable 5 compare to GPT-5.6?
| Set | fable5-return-frontier-glance |
|---|---|
| Options | 2, across 6 attributes |
| Last checked | 2026-07-01 |
| Used by | Claude Fable 5 Is Coming Back Online: When It Returns and How It Compares to ChatGPT's GPT-5.6 |
Benchmark scores and their sources
Which benchmark compares the two fairly?
| Set | fable5-sol-benchmarks |
|---|---|
| Options | 3, across 4 attributes |
| Last checked | 2026-07-10 |
| Used by | GPT-5.6 Sol vs Claude Fable 5: Cost, Benchmarks and What the Tests Actually Show |
List pricing per million tokens
Is GPT-5.6 Sol half the price of Claude Fable 5?
| Set | fable5-sol-pricing |
|---|---|
| Options | 3, across 4 attributes |
| Last checked | 2026-07-10 |
| Used by | GPT-5.6 Sol vs Claude Fable 5: Cost, Benchmarks and What the Tests Actually Show |
All rates are per 1M tokens.
Claude Fable 5 vs GPT-5.6 Sol at launch
What actually launched?
| Set | fable5-sol-specs |
|---|---|
| Options | 2, across 7 attributes |
| Last checked | 2026-07-10 |
| Used by | GPT-5.6 Sol vs Claude Fable 5: Cost, Benchmarks and What the Tests Actually Show |
GCAP vs F-35 specs
GCAP vs F-35: how do the specs compare?
| Set | gcap-f35-specs |
|---|---|
| Options | 2, across 9 attributes |
| Last checked | 2026-07-05 |
| Used by | GCAP vs F-35: Which Wins on Specs, and Which Costs Less? |
Confirmed facts, side by side
How do the three models compare on what's confirmed?
| Set | gemini35-3way-confirmed |
|---|---|
| Options | 3, across 5 attributes |
| Last checked | 2026-07-01 |
| Used by | Gemini 3.5 Pro vs GPT-5.6 vs Claude Fable 5: How the Newest Frontier Models Compare (2026) |
GPT-5.6 vs Gemini 3.5 Pro: availability
One of these models has shipped and one hasn't.
| Set | gemini35-sol-availability |
|---|---|
| Options | 2, across 5 attributes |
| Last checked | 2026-07-10 |
| Used by | Gemini 3.5 Pro vs GPT-5.6: Cost, Benchmarks, Tests and Context Window |
Context window: GPT-5.6 Sol vs Gemini
Which has the bigger context window, Gemini 3.5 Pro or GPT-5.6?
| Set | gemini35-sol-context |
|---|---|
| Options | 3, across 3 attributes |
| Last checked | 2026-07-10 |
| Used by | Gemini 3.5 Pro vs GPT-5.6: Cost, Benchmarks, Tests and Context Window |
API pricing: GPT-5.6 tiers vs Gemini Pro
Which is cheaper?
| Set | gemini35-sol-pricing |
|---|---|
| Options | 6, across 4 attributes |
| Last checked | 2026-07-10 |
| Used by | Gemini 3.5 Pro vs GPT-5.6: Cost, Benchmarks, Tests and Context Window |
Air cooler vs portable air conditioner, in a UK summer
Which one actually cools a room in British humidity?
| Set | uk-cooling |
|---|---|
| Options | 2, across 5 attributes |
| Last checked | 2026-06-28 |
| Used by | Air Cooler vs Portable Air Conditioner (2026): Which Should You Buy in the UK? |
Power draw and temperature drop are manufacturer ranges across the units surveyed, not a single model. Upfront cost is the UK retail range at the time each option was checked.