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 Opus 5.582.72Independent

    Anthropic

  2. Claude Fable 5.176.85Independent

    Anthropic

  3. GPT-6 Astra75.53Independent

    OpenAI

  4. Gemini 4 Argon73.03Independent

    Google DeepMind

  5. GPT-6.1 Sol71Independent

    OpenAI

  6. Gemini 3.8 Flash60.81Independent

    Google DeepMind

Agentic

BenchLM · 0 to 100

  1. Claude Opus 5.590.43Independent

    Anthropic

  2. Claude Fable 5.180.8Independent

    Anthropic

  3. Gemini 4 Argon78.78Independent

    Google DeepMind

  4. GPT-6.1 Sol76.35Independent

    OpenAI

  5. GPT-6 Astra75.68Independent

    OpenAI

  6. Gemini 3.8 Flash66.17Independent

    Google DeepMind

Reasoning

BenchLM · 0 to 100

  1. GPT-6 Astra93.3Independent

    OpenAI

  2. GPT-6.1 Sol90.5Independent

    OpenAI

  3. Gemini 4 Argon86.9Independent

    Google DeepMind

  4. Claude Opus 5.586.1Independent

    Anthropic

  5. Claude Fable 5.185.2Independent

    Anthropic

  6. Gemini 3.8 Flash74.3Independent

    Google DeepMind

Knowledge

BenchLM · 0 to 100

  1. Claude Opus 5.589.78Independent

    Anthropic

  2. Claude Fable 5.186.3Independent

    Anthropic

  3. GPT-6 Astra85.74Independent

    OpenAI

  4. GPT-6.1 Sol85.58Independent

    OpenAI

  5. Gemini 4 Argon80.88Independent

    Google DeepMind

  6. Gemini 3.8 Flash72.8Independent

    Google DeepMind

Arena

LM Arena · Elo

  1. Google DeepMind

  2. Anthropic

  3. Anthropic

  4. Google DeepMind

  5. GPT-6.1 Sol1,479.94Independent

    OpenAI

  6. GPT-6 Astra1,476.48Independent

    OpenAI

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 Opus 5.5, Coding: 82.72. Independent. Captured 2026-10-24.Claude Opus 5.5, Agentic: 90.43. Independent. Captured 2026-10-24.Claude Opus 5.5, Reasoning: 86.1. Independent. Captured 2026-10-24.Claude Opus 5.5, Knowledge: 89.78. Independent. Captured 2026-10-24.Claude Opus 5.5, Arena: 1,508.73. Independent. Captured 2026-10-24.Claude Fable 5.1, Coding: 76.85. Independent. Captured 2026-10-24.Claude Fable 5.1, Agentic: 80.8. Independent. Captured 2026-10-24.Claude Fable 5.1, Reasoning: 85.2. Independent. Captured 2026-10-24.Claude Fable 5.1, Knowledge: 86.3. Independent. Captured 2026-10-24.Claude Fable 5.1, Arena: 1,503.19. Independent. Captured 2026-10-24.GPT-6 Astra, Coding: 75.53. Independent. Captured 2026-10-24.GPT-6 Astra, Agentic: 75.68. Independent. Captured 2026-10-24.GPT-6 Astra, Reasoning: 93.3. Independent. Captured 2026-10-24.GPT-6 Astra, Knowledge: 85.74. Independent. Captured 2026-10-24.GPT-6 Astra, Arena: 1,476.48. Independent. Captured 2026-10-24.

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

Gemini 3.8 Flash

Released 2026-10-21 · 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
+5.59pts
71.26 to 76.85 Independent2026-10-24 / 2026-10-24
Agentic
+4.97pts
75.83 to 80.8 Independent2026-10-24 / 2026-10-24
Knowledge
+4.32pts
81.98 to 86.3 Independent2026-10-24 / 2026-10-24
Arena
-0.09Elo
1,503.28 to 1,503.19 Independent2026-10-24 / 2026-10-24

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 Opus 5.5CodingBenchLM.ai82.72Independent2026-10-24Claude Opus 5.5
Claude Fable 5.1CodingBenchLM.ai76.85Independent2026-10-24Claude Fable 5.1
GPT-6 AstraCodingBenchLM.ai75.53Independent2026-10-24GPT-6 Astra
Gemini 4 ArgonCodingBenchLM.ai73.03Independent2026-10-24Gemini 4 Argon
GPT-6.1 SolCodingBenchLM.ai71Independent2026-10-24GPT-6.1 Sol
Gemini 3.8 FlashCodingBenchLM.ai60.81Independent2026-10-24Gemini 3.8 Flash
Claude Opus 5.5AgenticBenchLM.ai90.43Independent2026-10-24Claude Opus 5.5
Claude Fable 5.1AgenticBenchLM.ai80.8Independent2026-10-24Claude Fable 5.1
Gemini 4 ArgonAgenticBenchLM.ai78.78Independent2026-10-24Gemini 4 Argon
GPT-6.1 SolAgenticBenchLM.ai76.35Independent2026-10-24GPT-6.1 Sol
GPT-6 AstraAgenticBenchLM.ai75.68Independent2026-10-24GPT-6 Astra
Gemini 3.8 FlashAgenticBenchLM.ai66.17Independent2026-10-24Gemini 3.8 Flash
GPT-6 AstraReasoningBenchLM.ai93.3Independent2026-10-24GPT-6 Astra
GPT-6.1 SolReasoningBenchLM.ai90.5Independent2026-10-24GPT-6.1 Sol
Gemini 4 ArgonReasoningBenchLM.ai86.9Independent2026-10-24Gemini 4 Argon
Claude Opus 5.5ReasoningBenchLM.ai86.1Independent2026-10-24Claude Opus 5.5
Claude Fable 5.1ReasoningBenchLM.ai85.2Independent2026-10-24Claude Fable 5.1
Gemini 3.8 FlashReasoningBenchLM.ai74.3Independent2026-10-24Gemini 3.8 Flash
Claude Opus 5.5KnowledgeBenchLM.ai89.78Independent2026-10-24Claude Opus 5.5
Claude Fable 5.1KnowledgeBenchLM.ai86.3Independent2026-10-24Claude Fable 5.1
GPT-6 AstraKnowledgeBenchLM.ai85.74Independent2026-10-24GPT-6 Astra
GPT-6.1 SolKnowledgeBenchLM.ai85.58Independent2026-10-24GPT-6.1 Sol
Gemini 4 ArgonKnowledgeBenchLM.ai80.88Independent2026-10-24Gemini 4 Argon
Gemini 3.8 FlashKnowledgeBenchLM.ai72.8Independent2026-10-24Gemini 3.8 Flash
Gemini 4 ArgonArenaLM Arena1,517.17Independent2026-10-24Gemini 4 Argon (High)10,083 votes
Claude Opus 5.5ArenaLM Arena1,508.73Independent2026-10-24Claude Opus 5.5 (High)10,322 votes
Claude Fable 5.1ArenaLM Arena1,503.19Independent2026-10-24Claude Fable 5.1 (Max)16,343 votes
Gemini 3.8 FlashArenaLM Arena1,495.7Independent2026-10-24Gemini 3.8 Flash (High)43,997 votes
GPT-6.1 SolArenaLM Arena1,479.94Independent2026-10-24GPT-6.1 Sol (Max)8,305 votes
GPT-6 AstraArenaLM Arena1,476.48Independent2026-10-24GPT-6 Astra (Max)14,076 votes
Additional readings for these models. Separate benchmarks, not substitutes for the five chart axes.
ModelMetric / sourceScore / provenanceCaptured
Claude Opus 5.5MultimodalGroundedBenchLM.ai91.8Independent2026-10-24
Claude Opus 5.5GDP.pdfEpoch AI30.6Independent2026-10-24
Claude Fable 5.1Humanity's Last ExamEpoch AI46.5Independent2026-10-24
Claude Fable 5.1GDP.pdfEpoch AI29.6Independent2026-10-24
GPT-6 AstraHumanity's Last ExamEpoch AI54.8Independent2026-10-24
Gemini 3.8 FlashMultimodalGroundedBenchLM.ai88.2Independent2026-10-24
Gemini 3.8 FlashHumanity's Last ExamEpoch AI44.5Independent2026-10-24
Open page →
Provider
InclusionAI
-
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
-
-