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 5.582.4Independent

    Anthropic

  2. Claude Fable 5.176.34Independent

    Anthropic

  3. GPT-6 Astra73.91Independent

    OpenAI

  4. Gemini 4 Argon71.95Independent

    Google DeepMind

  5. GPT-6.1 Sol69.28Independent

    OpenAI

  6. GPT-6.1 TerraNot reported

    OpenAI

Agentic

BenchLM · 0 to 100

  1. Claude Opus 5.589.34Independent

    Anthropic

  2. Claude Fable 5.180.35Independent

    Anthropic

  3. Gemini 4 Argon77.59Independent

    Google DeepMind

  4. GPT-6.1 Terra76.01Independent

    OpenAI

  5. GPT-6.1 Sol75.56Independent

    OpenAI

  6. GPT-6 Astra73.52Independent

    OpenAI

Reasoning

BenchLM · 0 to 100

  1. GPT-6 Astra80.43Independent

    OpenAI

  2. Claude Opus 5.579.95Independent

    Anthropic

  3. GPT-6.1 Sol79.94Independent

    OpenAI

  4. Gemini 4 Argon77.32Independent

    Google DeepMind

  5. Claude Fable 5.176.78Independent

    Anthropic

  6. GPT-6.1 Terra75.3Independent

    OpenAI

Knowledge

BenchLM · 0 to 100

  1. Claude Opus 5.588.17Independent

    Anthropic

  2. Claude Fable 5.184.7Independent

    Anthropic

  3. GPT-6.1 Sol84.13Independent

    OpenAI

  4. GPT-6 Astra83.81Independent

    OpenAI

  5. Gemini 4 Argon79.36Independent

    Google DeepMind

  6. GPT-6.1 Terra76.47Independent

    OpenAI

Arena

LM Arena · Elo

  1. Google DeepMind

  2. Anthropic

  3. Anthropic

  4. GPT-6.1 Sol1,479.94Independent

    OpenAI

  5. GPT-6 Astra1,476.48Independent

    OpenAI

  6. GPT-6.1 TerraNot reported

    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: 82.4. Independent. Captured 2026-11-11.Claude Opus 5.5, Agentic: 89.34. Independent. Captured 2026-11-11.Claude Opus 5.5, Reasoning: 79.95. Independent. Captured 2026-11-11.Claude Opus 5.5, Knowledge: 88.17. Independent. Captured 2026-11-11.Claude Opus 5.5, Arena: 1,508.73. Independent. Captured 2026-10-26.Claude Fable 5.1, Coding: 76.34. Independent. Captured 2026-11-11.Claude Fable 5.1, Agentic: 80.35. Independent. Captured 2026-11-11.Claude Fable 5.1, Reasoning: 76.78. Independent. Captured 2026-11-11.Claude Fable 5.1, Knowledge: 84.7. Independent. Captured 2026-11-11.Claude Fable 5.1, Arena: 1,503.19. Independent. Captured 2026-10-26.Gemini 4 Argon, Coding: 71.95. Independent. Captured 2026-11-11.Gemini 4 Argon, Agentic: 77.59. Independent. Captured 2026-11-11.Gemini 4 Argon, Reasoning: 77.32. Independent. Captured 2026-11-11.Gemini 4 Argon, Knowledge: 79.36. Independent. Captured 2026-11-11.Gemini 4 Argon, Arena: 1,517.17. Independent. Captured 2026-10-26.

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

GPT-6.1 Terra

Released 2026-11-03 · 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
+5.37pts
70.97 to 76.34 Independent2026-11-11 / 2026-11-11
Agentic
+6.33pts
74.02 to 80.35 Independent2026-11-11 / 2026-11-11
Reasoning
+4.75pts
72.03 to 76.78 Independent2026-11-11 / 2026-11-11
Knowledge
+4.54pts
80.16 to 84.7 Independent2026-11-11 / 2026-11-11
Arena
-0.09Elo
1,503.28 to 1,503.19 Independent2026-10-26 / 2026-10-26

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.ai82.4Independent2026-11-11Claude Opus 5.5
Claude Fable 5.1CodingBenchLM.ai76.34Independent2026-11-11Claude Fable 5.1
GPT-6 AstraCodingBenchLM.ai73.91Independent2026-11-11GPT-6 Astra
Gemini 4 ArgonCodingBenchLM.ai71.95Independent2026-11-11Gemini 4 Argon
GPT-6.1 SolCodingBenchLM.ai69.28Independent2026-11-11GPT-6.1 Sol
GPT-6.1 TerraCodingBenchLM.aiNot reportedNot reportedNot reported
Claude Opus 5.5AgenticBenchLM.ai89.34Independent2026-11-11Claude Opus 5.5
Claude Fable 5.1AgenticBenchLM.ai80.35Independent2026-11-11Claude Fable 5.1
Gemini 4 ArgonAgenticBenchLM.ai77.59Independent2026-11-11Gemini 4 Argon
GPT-6.1 TerraAgenticBenchLM.ai76.01Independent2026-11-11GPT-6.1 Terra
GPT-6.1 SolAgenticBenchLM.ai75.56Independent2026-11-11GPT-6.1 Sol
GPT-6 AstraAgenticBenchLM.ai73.52Independent2026-11-11GPT-6 Astra
GPT-6 AstraReasoningBenchLM.ai80.43Independent2026-11-11GPT-6 Astra
Claude Opus 5.5ReasoningBenchLM.ai79.95Independent2026-11-11Claude Opus 5.5
GPT-6.1 SolReasoningBenchLM.ai79.94Independent2026-11-11GPT-6.1 Sol
Gemini 4 ArgonReasoningBenchLM.ai77.32Independent2026-11-11Gemini 4 Argon
Claude Fable 5.1ReasoningBenchLM.ai76.78Independent2026-11-11Claude Fable 5.1
GPT-6.1 TerraReasoningBenchLM.ai75.3Independent2026-11-11GPT-6.1 Terra
Claude Opus 5.5KnowledgeBenchLM.ai88.17Independent2026-11-11Claude Opus 5.5
Claude Fable 5.1KnowledgeBenchLM.ai84.7Independent2026-11-11Claude Fable 5.1
GPT-6.1 SolKnowledgeBenchLM.ai84.13Independent2026-11-11GPT-6.1 Sol
GPT-6 AstraKnowledgeBenchLM.ai83.81Independent2026-11-11GPT-6 Astra
Gemini 4 ArgonKnowledgeBenchLM.ai79.36Independent2026-11-11Gemini 4 Argon
GPT-6.1 TerraKnowledgeBenchLM.ai76.47Independent2026-11-11GPT-6.1 Terra
Gemini 4 ArgonArenaLM Arena1,517.17Independent2026-10-26Gemini 4 Argon (High)10,083 votes
Claude Opus 5.5ArenaLM Arena1,508.73Independent2026-10-26Claude Opus 5.5 (High)10,322 votes
Claude Fable 5.1ArenaLM Arena1,503.19Independent2026-10-26Claude Fable 5.1 (Max)16,343 votes
GPT-6.1 SolArenaLM Arena1,479.94Independent2026-10-26GPT-6.1 Sol (Max)8,305 votes
GPT-6 AstraArenaLM Arena1,476.48Independent2026-10-26GPT-6 Astra (Max)14,076 votes
GPT-6.1 TerraArenaLM ArenaNot reportedNot reportedNot reported
Additional readings for these models. Separate benchmarks, not substitutes for the five chart axes.
ModelMetric / sourceScore / provenanceCaptured
Claude Opus 5.5MultimodalGroundedBenchLM.ai84.44Independent2026-11-11
Claude Opus 5.5GDP.pdfEpoch AI30.6Independent2026-11-11
Claude Fable 5.1Humanity's Last ExamEpoch AI46.5Independent2026-11-11
Claude Fable 5.1GDP.pdfEpoch AI29.6Independent2026-11-11
Claude Fable 5.1MultimodalGroundedBenchLM.ai81.2Independent2026-11-11
Gemini 4 ArgonGDP.pdfEpoch AI28.4Independent2026-11-11
GPT-6 AstraHumanity's Last ExamEpoch AI54.8Independent2026-11-11
GPT-6 AstraMultimodalGroundedBenchLM.ai78.93Independent2026-11-11
GPT-6.1 SolMultimodalGroundedBenchLM.ai78.36Independent2026-11-11
GPT-6.1 TerraMultimodalGroundedBenchLM.ai77.22Independent2026-11-11
Open page →
Provider
Google DeepMind
-
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
-
-