Benchmarks

Compare AI models

Pick two models to see release dates, benchmark scores, and community ratings side by side.

Frontier benchmarks

Frontier board

6 releases. Five ways to compare.

Selected for recent releases and benchmark coverage, not a single overall rank. Each column sorts the same models by its own score. No reading means no bar.

○ Independent evaluation · ◆ Vendor or self-reported, labeled per reading.

Coding

BenchLM · 0 to 100

  1. Claude Fable 5.176.76Independent

    Anthropic

  2. GPT-6 Astra75.42Independent

    OpenAI

  3. Gemini 4 Argon72.25Independent

    Google DeepMind

  4. GPT-6.1 Sol70.89Independent

    OpenAI

  5. Claude Opus 570.63Independent

    Anthropic

  6. Muse Spark Open56.06Independent

    Meta

Agentic

BenchLM · 0 to 100

  1. Claude Fable 5.180.93Independent

    Anthropic

  2. Claude Opus 578.52Independent

    Anthropic

  3. Gemini 4 Argon77.32Independent

    Google DeepMind

  4. GPT-6.1 Sol76.29Independent

    OpenAI

  5. GPT-6 Astra74.89Independent

    OpenAI

  6. Muse Spark Open60.19Independent

    Meta

Reasoning

BenchLM · 0 to 100

  1. GPT-6 Astra93.3Independent

    OpenAI

  2. GPT-6.1 Sol90.5Independent

    OpenAI

  3. Claude Fable 5.185.2Independent

    Anthropic

  4. Claude Opus 581Independent

    Anthropic

  5. Gemini 4 ArgonNot reported

    Google DeepMind

  6. Muse Spark OpenNot reported

    Meta

Knowledge

BenchLM · 0 to 100

  1. Claude Fable 5.186.65Independent

    Anthropic

  2. GPT-6 Astra85.93Independent

    OpenAI

  3. GPT-6.1 Sol85.83Independent

    OpenAI

  4. Claude Opus 581.8Independent

    Anthropic

  5. Gemini 4 Argon80.24Independent

    Google DeepMind

  6. Muse Spark Open64.57Independent

    Meta

Arena

LM Arena · Elo

  1. Gemini 4 Argon1,523.9Independent

    Google DeepMind

  2. Anthropic

  3. Claude Opus 51,489.99Independent

    Anthropic

  4. GPT-6.1 Sol1,483.85Independent

    OpenAI

  5. GPT-6 Astra1,477.32Independent

    OpenAI

  6. Muse Spark OpenNot reported

    Meta

Score links open the source; hover for capture details. Bar lengths start at zero. Arena lengths use the full public board maximum.

The shape of the scores

First three featured models. Toggle a name to isolate a line. Missing readings leave gaps, not zeroes.

CodingAgenticReasoningKnowledgeArena050100Claude Fable 5.1, Coding: 76.76. Independent. Captured 2026-10-16.Claude Fable 5.1, Agentic: 80.93. Independent. Captured 2026-10-16.Claude Fable 5.1, Reasoning: 85.2. Independent. Captured 2026-10-16.Claude Fable 5.1, Knowledge: 86.65. Independent. Captured 2026-10-16.Claude Fable 5.1, Arena: 1,502.29. Independent. Captured 2026-10-16.GPT-6 Astra, Coding: 75.42. Independent. Captured 2026-10-16.GPT-6 Astra, Agentic: 74.89. Independent. Captured 2026-10-16.GPT-6 Astra, Reasoning: 93.3. Independent. Captured 2026-10-16.GPT-6 Astra, Knowledge: 85.93. Independent. Captured 2026-10-16.GPT-6 Astra, Arena: 1,477.32. Independent. Captured 2026-10-16.GPT-6.1 Sol, Coding: 70.89. Independent. Captured 2026-10-16.GPT-6.1 Sol, Agentic: 76.29. Independent. Captured 2026-10-16.GPT-6.1 Sol, Reasoning: 90.5. Independent. Captured 2026-10-16.GPT-6.1 Sol, Knowledge: 85.83. Independent. Captured 2026-10-16.GPT-6.1 Sol, Arena: 1,483.85. Independent. Captured 2026-10-16.

3 of 3 series shown.

Axes share drawing space, not meaning. Arena is Elo divided by the current board maximum; it is not a percentage accuracy.

The newest arrival

Muse Spark Open

Released 2026-10-15 · At least two readings

No predecessor is linked in the catalog yet. We do not infer a generation jump from a name.

Latest release with linked lineage

Claude Fable 5.1 vs Claude Fable 5

Coding
+5.53pts
71.23 to 76.76 Independent2026-10-16 / 2026-10-16
Agentic
+4.97pts
75.96 to 80.93 Independent2026-10-16 / 2026-10-16
Knowledge
+4.3pts
82.35 to 86.65 Independent2026-10-16 / 2026-10-16
Arena
-1.32Elo
1,503.6 to 1,502.29 Independent2026-10-16 / 2026-10-16

Latest snapshots, not a controlled before-and-after trial. Capture dates and evaluation setups may differ.

Scores and sources

Frontier board: original scores. Not reported is missing, not zero.
ModelMetricScore / provenanceCapturedSource label / votes
Claude Fable 5.1CodingBenchLM.ai76.76Independent2026-10-16Claude Fable 5.1
GPT-6 AstraCodingBenchLM.ai75.42Independent2026-10-16GPT-6 Astra
Gemini 4 ArgonCodingBenchLM.ai72.25Independent2026-10-16Gemini 4 Argon
GPT-6.1 SolCodingBenchLM.ai70.89Independent2026-10-16GPT-6.1 Sol
Claude Opus 5CodingBenchLM.ai70.63Independent2026-10-16Claude Opus 5
Muse Spark OpenCodingBenchLM.ai56.06Independent2026-10-16Muse Spark Open
Claude Fable 5.1AgenticBenchLM.ai80.93Independent2026-10-16Claude Fable 5.1
Claude Opus 5AgenticBenchLM.ai78.52Independent2026-10-16Claude Opus 5
Gemini 4 ArgonAgenticBenchLM.ai77.32Independent2026-10-16Gemini 4 Argon
GPT-6.1 SolAgenticBenchLM.ai76.29Independent2026-10-16GPT-6.1 Sol
GPT-6 AstraAgenticBenchLM.ai74.89Independent2026-10-16GPT-6 Astra
Muse Spark OpenAgenticBenchLM.ai60.19Independent2026-10-16Muse Spark Open
GPT-6 AstraReasoningBenchLM.ai93.3Independent2026-10-16GPT-6 Astra
GPT-6.1 SolReasoningBenchLM.ai90.5Independent2026-10-16GPT-6.1 Sol
Claude Fable 5.1ReasoningBenchLM.ai85.2Independent2026-10-16Claude Fable 5.1
Claude Opus 5ReasoningBenchLM.ai81Independent2026-10-16Claude Opus 5
Gemini 4 ArgonReasoningBenchLM.aiNot reportedNot reportedNot reported
Muse Spark OpenReasoningBenchLM.aiNot reportedNot reportedNot reported
Claude Fable 5.1KnowledgeBenchLM.ai86.65Independent2026-10-16Claude Fable 5.1
GPT-6 AstraKnowledgeBenchLM.ai85.93Independent2026-10-16GPT-6 Astra
GPT-6.1 SolKnowledgeBenchLM.ai85.83Independent2026-10-16GPT-6.1 Sol
Claude Opus 5KnowledgeBenchLM.ai81.8Independent2026-10-16Claude Opus 5
Gemini 4 ArgonKnowledgeBenchLM.ai80.24Independent2026-10-16Gemini 4 Argon
Muse Spark OpenKnowledgeBenchLM.ai64.57Independent2026-10-16Muse Spark Open
Gemini 4 ArgonArenaLM Arena1,523.9Independent2026-10-16Gemini 4 Argon (High)4,904 votes
Claude Fable 5.1ArenaLM Arena1,502.29Independent2026-10-16Claude Fable 5.1 (Max)14,590 votes
Claude Opus 5ArenaLM Arena1,489.99Independent2026-10-16Claude Opus 5 (Max)32,495 votes
GPT-6.1 SolArenaLM Arena1,483.85Independent2026-10-16gpt-6.1-sol-max6,320 votes
GPT-6 AstraArenaLM Arena1,477.32Independent2026-10-16gpt-6-astra-max12,163 votes
Muse Spark OpenArenaLM ArenaNot reportedNot reportedNot reported
Additional readings for these models. Separate benchmarks, not substitutes for the five chart axes.
ModelMetric / sourceScore / provenanceCaptured
Claude Fable 5.1Humanity's Last ExamEpoch AI46.5Independent2026-10-16
Claude Fable 5.1GDP.pdfEpoch AI29.6Independent2026-10-16
GPT-6 AstraHumanity's Last ExamEpoch AI54.8Independent2026-10-16
Claude Opus 5MultimodalGroundedBenchLM.ai92.2Independent2026-10-16
Claude Opus 5GDP.pdfEpoch AI24Independent2026-10-16
Open page →
Provider
NVIDIA
-
Out yet?
No
-
Status
Speculated
-
Release date
-
-
Vibe rating?OutYet's community rating: signed-in users score the model 1–10. Shown as the average and the number of votes.
-
-
Predecessor
-
-
Successor
-
-