Command A Plus 05 2026 BF16 vs Hy3

At a Glance

Compare
Hy3Tencent
Intelligence, Cost, and Efficiency
IntelligenceHigher is better · MM Intelligence v4.4UnrankedNot in the 57-model eligible cohort#25 of 5750.1 score · 1/3 sources · single-source provisional · missing LiveBench, ARC-AGI-2 · full-core range 16.7–83.4
Pricing and Limits
Input priceFrom · USD / 1M tokensNot reported$0.13Deepinfra ↗ · Oct 1, 2026
Output priceFrom · USD / 1M tokensNot reported$0.528Openrouter ↗ · Oct 19, 2026
Context windowMaximum documented tokens200K262K
Model facts checkedAug 28, 2026View model evidence →Aug 28, 2026View model evidence →

Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →

Available Benchmarks

All benchmark results →
No Protocol-Matched Benchmark Yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.

Side-by-Side Facts

Fieldcommand-a-plus-05-2026-bf16Hy3
DeveloperCohereTencent
FamilyCommand A Plus 05Hy3
Modelcommand-a-plus-05-2026-bf16Hy3
Versioncommand-a-plus-05-2026-bf16Hy3
Lifecycleactiveactive
ReleasedUnknownUnknown
Knowledge cutoffUnknownUnknown
Input modalitiesText, ImageText
Output modalitiesTextText
Context window200K262K
Total parameters218.8B298.8B
Active parameters25B21B
Licenseapache-2.0apache-2.0
Open weightsYesYes
API availableUnknownYes
Self-hostableYesYes
Provider accessUnknownDeepinfra (Standard), Hugging Face (Standard), Openrouter (Standard)
Capabilitieschat, generation, toolschat, generation, tools

Command A Plus 05 2026 BF16 Capabilities

chatgenerationtools
Serving providers0
Canonical IDCohereLabs/command-a-plus-05-2026-bf16

Hy3 Capabilities

chatgenerationtools
Serving providers3
Canonical IDtencent/Hy3

Primary Evidence

Sources and Freshness

Questions

Command A Plus 05 2026 BF16 vs Hy3 FAQs

Is Command A Plus 05 2026 BF16 or Hy3 better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Command A Plus 05 2026 BF16 and Hy3, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Command A Plus 05 2026 BF16 or Hy3?+

Only Hy3 has a directly sourced input price: $0.13 per million tokens. Only Hy3 has a directly sourced output price: $0.528 per million tokens.

Which has a larger context window, Command A Plus 05 2026 BF16 or Hy3?+

Hy3 has the larger sourced context window. Command A Plus 05 2026 BF16 supports 200,000 tokens and Hy3 supports 262,144 tokens.

Which performs better in benchmarks, Command A Plus 05 2026 BF16 or Hy3?+

There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.

Can Command A Plus 05 2026 BF16 or Hy3 be self-hosted?+

Both models have the same sourced self-hosting status: supported. Command A Plus 05 2026 BF16 is open weight; Hy3 is open weight.

Can Command A Plus 05 2026 BF16 and Hy3 understand images?+

Command A Plus 05 2026 BF16 is documented with image input; Hy3 is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Command A Plus 05 2026 BF16 or Hy3?+

Command A Plus 05 2026 BF16 has a sourced maximum output of 65,536 tokens; Hy3's maximum output is not reported. A larger limit cannot be determined.

Do Command A Plus 05 2026 BF16 and Hy3 support reasoning and tool use?+

Command A Plus 05 2026 BF16: tool calling and image input. Hy3: tool calling. Feature support does not establish relative quality.

Which is available from more inference providers, Command A Plus 05 2026 BF16 or Hy3?+

Command A Plus 05 2026 BF16 has 0 sourced provider routes; Hy3 has 3, so Hy3 has broader tracked availability.

Which offers better value, Command A Plus 05 2026 BF16 or Hy3?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback