VerdictPal
Join

Models / Multiverse

HyperNova 60B 2605

HyperNova · Released 2026-05-06

Multiverse Computing's May 2026 open-source 60B update, evaluated by Artificial Analysis on 11 Jun. The release emphasizes coding, native tool calling, OpenAI-style function schemas, structured outputs, and configurable reasoning effort.

Compressed open model for coding agents and tool-augmented workflows when you want Apache-licensed weights instead of a closed API.

#41 of 51 on AA Index · current snapshot
18 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite34
Context128K
Input / 1M—
Output / 1M—
Knowledge cutoffopen
Output speed381 t/s
TTFT (default API)0.60s
Statuslightweight
ReasoningCodingAgenticLong context
Reasoning
73
Coding
33
Agentic
18
Long context
32

39average across 4 tested families

Benchmark placements

Where HyperNova 60B 2605 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
AA output speedPerformance#2/ 69Artificial Analysis2026-07-21
IFBenchReasoning#37/ 5766Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#50/ 6515Artificial Analysis2026-07-21
AA time to first tokenPerformance#53/ 69Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#57/ 6718Artificial Analysis2026-07-21
AA-LCRLong context#59/ 6432Artificial Analysis2026-07-21
SciCodeCoding#59/ 6533Artificial Analysis2026-07-21
Terminal-BenchAgentic#60/ 6918Artificial Analysis2026-07-21
GPQA DiamondReasoning#61/ 6973Artificial Analysis2026-07-21
τ³-Bench BankingAgentic#62/ 645Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where HyperNova 60B 2605 shows up, it's highlighted.

ReasoningHyperNova 60B 2605 · 73
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
CodingHyperNova 60B 2605 · 33
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticHyperNova 60B 2605 · 18
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextHyperNova 60B 2605 · 32
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
Newest receipts

Benchmark rows added to the public ledger for HyperNova 60B 2605 in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context31.67%Artificial Analysis2
AA output speedPerformance381 t/sArtificial Analysis2
AA time to first tokenPerformance0.60sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning17.8%Artificial Analysis2
GPQA DiamondReasoning73.3%Artificial Analysis2
Humanity's Last ExamReasoning15.1%Artificial Analysis2
IFBenchReasoning66.46%Artificial Analysis2
SciCodeCoding33%Artificial Analysis2
τ³-Bench BankingAgentic5.36%Artificial Analysis2
Terminal-BenchAgentic18.35%Artificial Analysis2
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning73
Coding33
Agentic18
Long context32
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

Full benchmark ledger

Every catalog benchmark for HyperNova 60B 2605. Scores link to the original source; gaps mean no public row exists yet.

10 sourced rows

10 of 32 catalog benchmarks have a sourced row for HyperNova 60B 2605.

Reasoning

Coding

Agentic

Long context

Performance

Sources