Typesafe vs OpenAI

Each lab shows its best-ranked model on every board. One row per board where at least one is ranked, from each board's current capture.

Typesafe
OpenAI

Add:

Head to head on 1 board: OpenAI places best on 1 and Typesafe places best on 0. Both ranked on 1 of 26 boards.

Board	Read	Typesafe	OpenAI
Chat2
MultiChallengeScoreyesterday	Nov 9yesterday		#182.0%GPT-6.1 Sol
Text ArenaArena ratingyesterday	Nov 9yesterday		#191,485GPT-5.6 Sol
Reasoning7
HLEAccuracyyesterday	Nov 9yesterday		#154.8%GPT-6 Astra
Epoch ECIECIyesterday	Nov 9yesterday		#1169.1GPT-6 Astra
ARC-AGI-2Scoreyesterday	Nov 9yesterday		#195.0%GPT-6 Astra
GPQA DiamondAccuracyyesterday	Nov 9yesterday		#295.8%GPT-6 Astra
AA IntelligenceIndexyesterday	Nov 9yesterday		#356.9GPT-6 Astra
MMLU-ProAccuracy · staleyesterday	Nov 9yesterday		#389.3%o1
LiveBenchGlobal averageyesterday	Nov 9yesterday		#482.2%GPT-6 Astra
Coding4
Aider PolyglotPass rate · staleyesterday	Nov 9yesterday		#188.0%GPT-5
WebDev ArenaArena ratingyesterday	Nov 9yesterday		#31,770GPT-6 Astra
SWE-Bench ProResolvedyesterday	Nov 9yesterday		#490.2%GPT-6 Astra
SWE-bench VerifiedResolved · staleyesterday	Nov 9yesterday		#672.8%GPT-5.2
Agents and tools3
Search ArenaArena ratingyesterday	Nov 9yesterday		#11,255GPT-5.6 Sol
BFCLOverall accuracy · staleyesterday	Nov 9yesterday		#763.0%o3
MCP AtlasPass rateyesterday	Nov 9yesterday		#1481.8%GPT-5.6
Vision2
Document ArenaArena ratingyesterday	Nov 9yesterday		#51,486GPT-5.6 Sol
Vision ArenaArena ratingyesterday	Nov 9yesterday		#81,293GPT-6.1 Sol
Image2
Text-to-ImageArena ratingyesterday	Nov 9yesterday		#11,429GPT Image 2.5 Sunburst
Image EditArena ratingyesterday	Nov 9yesterday		#11,517GPT Image 2.5 Sunburst
Video1
Text-to-VideoArena ratingyesterday	Nov 9yesterday		#131,367Sora 2 Pro
Speech2
Open ASRAverage WERyesterday	Nov 9yesterday		#186.80 WERgpt-transcribe (openai)
Speech ArenaArena ratingyesterday	Nov 9yesterday		#421,107TTS 1 Hd
Speed1
AA SpeedOutput speedyesterday	Nov 9yesterday		#1522 tok/sGPT-6.1 Sol
Price1
AA PriceBlended priceyesterday	Nov 9yesterday		#6$2.00GPT-6.1 Terra
Usage1
OpenRouterWeekly tokensyesterday	Nov 9yesterday	#133.1T tokJev 1.13	#47.2T tokbest of the pickedGPT-6 Luna

Green marks the best placing among the picked where two or more are ranked; ties are marked for each. Ranks are each board's own order (lower is better), scores as the board published them. Dash: not on that board.

More comparisons