Head to head on 15 boards: DeepSeek places best on 8, Meta places best on 6 and Inception places best on 1. All 3 ranked on 1 of 25 boards.
Two at a time on this screen. Tap one to swap it in.
| Board | Read |  Inception |  Meta |  DeepSeek |
|---|
| Chat2 | | | | |
|---|
 MultiChallengeScoretodaytoday | Oct 21todaytoday | | #275.5%best of the pickedMuse Spark | #2646.1%DeepSeek V3P1 |
 Text ArenaArena ratingtodaytoday | Oct 21todaytoday | | #81,494best of the pickedMuse Spark 1.3 | #341,475DeepSeek V4.1 Flash |
| Reasoning7 | | | | |
|---|
 LiveBenchGlobal averagetodaytoday | Oct 21todaytoday | | #681.6%best of the pickedMuse Spark 1.3 | #881.1%DeepSeek V4.1 Flash |
 Epoch ECIECItodaytoday | Oct 21todaytoday | | #12161.8best of the pickedMuse Wonder | #32155.9DeepSeek V4.1 Flash |
 ARC-AGI-2Scoretodaytoday | Oct 21todaytoday | | #800.0%Llama 4 Maverick Instruct | #2172.9%best of the pickedDeepSeek V4.1 Flash |
| GPQA DiamondAccuracytodaytoday | Oct 21todaytoday | | #4389.8%Muse Spark | #2591.7%best of the pickedDeepSeek V4 Pro 0813 |
 MMLU-ProAccuracy · staletodaytoday | Oct 21todaytoday | | #4782.8%Llama4 Behemoth | #3385.0%best of the pickedDeepSeek-V3.2 |
 AA IntelligenceIndextodaytoday | Oct 21todaytoday | | #256.0Muse Wonder Full | |
| HLEAccuracytodaytoday | Oct 21todaytoday | | #740.6%Muse Spark | |
| Coding4 | | | | |
|---|
 Aider PolyglotPass rate · staletodaytoday | Oct 21todaytoday | | #4315.6%Llama 4 Maverick Instruct | #874.2%best of the pickedDeepSeek-V3.2 |
| WebDev ArenaArena ratingtodaytoday | Oct 21todaytoday | | #101,656best of the pickedMuse Spark 1.3 | #191,619DeepSeek V4.1 Flash |
 SWE-bench VerifiedResolved · staletodaytoday | Oct 21todaytoday | | #3621.0%Llama 4 Maverick Instruct | #1170.0%best of the pickedDeepSeek-V3.2 |
| SWE-Bench ProResolvedtodaytoday | Oct 21todaytoday | | #490.2%Muse Wonder 1.0 Max Effort | |
| Agents and tools2 | | | | |
|---|
 BFCLOverall accuracy · staletodaytoday | Oct 21todaytoday | | #3637.3%Llama 4 Maverick 17b 128e | #1256.7%best of the pickedDeepSeek-V3.2 |
| MCP AtlasPass ratetodaytoday | Oct 21todaytoday | | #188.1%Muse Spark 1.1 | |
| Vision2 | | | | |
|---|
| Vision ArenaArena ratingtodaytoday | Oct 21todaytoday | | #71,294best of the pickedMuse Spark | #391,260DeepSeek V4.1 Flash |
| Document ArenaArena ratingtodaytoday | Oct 21todaytoday | | #121,471Muse Spark 1.3 | |
| Image2 | | | | |
|---|
| Image EditArena ratingtodaytoday | Oct 21todaytoday | | #71,403Muse Image | |
| Text-to-ImageArena ratingtodaytoday | Oct 21todaytoday | | #81,274Muse Image | |
| Video1 | | | | |
|---|
| Text-to-VideoArena ratingtodaytoday | Oct 21todaytoday | | #91,456Muse Video | |
| Speech2 | | | | |
|---|
 Open ASRAverage WERtodaytoday | Oct 21todaytoday | | #356.48 WERmuse-voice-transcribe (meta) | |
| Speech ArenaArena ratingtodaytoday | Oct 21todaytoday | | #95847Metavoice V1 | |
| Speed1 | | | | |
|---|
| AA SpeedOutput speedtodaytoday | Oct 21todaytoday | #3781 tok/sbest of the pickedMercury 2.5 | #7281 tok/sMuse Spark 1.3 | #16209 tok/sDeepSeek V4.1 Flash |
| Price1 | | | | |
|---|
| AA PriceBlended pricetodaytoday | Oct 21todaytoday | | #15$2.00Muse Spark 1.3 | #8$0.53best of the pickedDeepSeek V4.1 Flash |
| Usage1 | | | | |
|---|
 OpenRouterWeekly tokenstodaytoday | Oct 21todaytoday | | #123.3T tokMuse Spark 1.3 Contributor | #127.3T tokbest of the pickedDeepSeek V4.1 Flash |
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.
Modelsby Ibis