Benchmarks of HyperNova 60B 260516
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding3
Agents3
Documents1
Legacy · saturated or no longer reported2
No benchmark matches
—per task?
API price not publicprice
—output speed?
131Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunalow+83%—$0.005Function calling only with none · Chat Completions+3
OpenQwen3.8 27Bxhigh×2.9—$1.01max_tokens range · QwenCloud+4BetterGPT-5.6 Lunalow+79%—$0.01
BetterMiMo v2.5thinkingOpen+86%—$0.019Memory (4-bit): 35 GB → 186 GB
BetterClaude Haiku 5.5low×2.5—$0.024Remove sampling parameters+5ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunalow+83%—$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+79%—$0.01MiMo v2.5thinkingOpen+86%—$0.019Memory (4-bit): 35 GB → 186 GBClaude Haiku 5.5low×2.5—$0.024Remove sampling parameters+5GPT-5 Minihigh+43%—$0.053ModelScoreCostPer taskWhat changes
Qwen3.8 27BxhighOpen×2.9—$1.01max_tokens range · QwenCloud+4
Nemotron 3.5 Super VLOpen×2.3—$0.19Memory (4-bit): 35 GB → 75 GBIK2 Horizon MoVA 36B A4BthinkingOpen×2.2—$1 / $4
Ling 3.0 Flash VLthinkingOpen×2.1—$0.06 / $0.18Memory (4-bit): 35 GB → 75 GBQwen 3.5 27BthinkingOpen+95%—$0.30 / $2.40Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✓ 48 GB GPU · compressed✓ 80 GB GPU · 8-bit
LicenceApache-2.0free for commercial use
Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam16.6#137
AA Omniscience Index-54.6#236
CritPt (physics)0.9#130
AA Intelligence Index 4.3.2≈11.7#185
AA Omniscience · Accuracy15.2#230
AA-LCR (long context) 1.136.3#209
GPQA Diamond73.3#166
Coding
Terminal-Bench 2.118.4#114
Agents & Tool Use
τ³-Banking · AA5.6#113
AA-Briefcase 1.1 · Elo231.9#114
τ²-bench · AA63.2#101
Writing & Language
IFBench (instructions)66.5#67
FAQ
How much does HyperNova 60B 2605 cost?›
There is no per-unit API price: API price not public.
Is HyperNova 60B 2605 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is HyperNova 60B 2605, and what is it best at?›
#137 of 334 in Chat & Knowledge, #75 of 132 in Coding, #122 of 175 in Agents & Tool Use, #67 of 245 in Writing & Language.
Is HyperNova 60B 2605 better than Sonar Reasoning Pro?›
On AA Intelligence Index 4.3.2, HyperNova 60B 2605 scores 11.7 vs 11.8 — about the same.
What is the context window of HyperNova 60B 2605?›
131K tokens.
When was HyperNova 60B 2605 released? Is there a newer version?›
Released 2026-05-26. It is the current version in its line.
Is HyperNova 60B 2605 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run HyperNova 60B 2605 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can HyperNova 60B 2605 read images?›
No, it accepts text only.
What is HyperNova 60B 2605?›
HyperNova 60B 2605 is an open-weights language model from Multiverse Computing, released May 2026.
What are the best alternatives to HyperNova 60B 2605?›
GPT-6 Luna (better), Qwen3.8 27B (open weights).