Pick Hunyuan Hy4 Preview for gpqa diamond (92.3) or terminal-bench (85.4). Pick Muse Spark 1.3 for agentic coding with ~20% fewer tool calls and ~25% fewer tokens than muse spark 1.2 or deepswe v1.1 long-horizon software engineering (75.4). Choose Hunyuan Hy4 Preview if you need self-hosting or data privacy; Muse Spark 1.3 if you want a managed API.
Hunyuan Hy4 Preview (Tencent, China) and Muse Spark 1.3 (Meta, US) line up two different AI ecosystems against each other — a comparison that is as much about cost philosophy and openness as raw capability. Hunyuan Hy4 Preview is tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline. Muse Spark 1.3 is meta's September 2, 2026 agentic-coding model update, cutting tool calls and token usage versus Muse Spark 1.2 while its highest-reasoning mode remains gated for safety review. They diverge most on price and open vs. closed weights — each quantified below from the models' real specs.
Key differences
Price: Hunyuan Hy4 Preview is about 1.5× cheaper on input ($0.834/$2.501 per 1M tokens vs $1.25/$4.25 per 1M tokens) — modest, but it adds up at steady volume.
Context window: both advertise 1M+ tokens (~1,500 pages). Tie on paper — test on your own long inputs, since usable recall varies by model.
Ecosystem: this is a China-vs-US matchup — they differ in pricing philosophy, data-residency options, and tooling ecosystems, not only benchmarks.
Specifications
Spec
Hunyuan Hy4 Preview
Muse Spark 1.3
Provider
Tencent (China)
Meta (US)
Released
August 28, 2026
September 2, 2026
Context window
1M+ tokens (~1,500 pages)
1M tokens (~1,500 pages)
Price (in/out)
$0.834/$2.501 per 1M tokens
$1.25/$4.25 per 1M tokens
Open weight?
Yes — self-hostable
No — API only
Modalities
text
text, image, video
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
98.1%
Who wins what
GPQA Diamond (92.3): Hunyuan Hy4 Preview — Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline — and it runs cheaper at $0.834/$2.501 per 1M tokens.
Terminal-Bench (85.4): Hunyuan Hy4 Preview — Muse Spark 1.3 is comparatively weak here — no official SWE-bench Verified score published
SWE-bench Multilingual (82.9): Hunyuan Hy4 Preview — Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline — and its weights are open while Muse Spark 1.3 is API-only.
Agentic coding with ~20% fewer tool calls and ~25% fewer tokens than Muse Spark 1.2: Muse Spark 1.3 — Meta's September 2, 2026 agentic-coding model update, cutting tool calls and token usage versus Muse Spark 1.2 while its highest-reasoning mode remains gated for safety review — and it is the newer of the two.
DeepSWE v1.1 long-horizon software engineering (75.4): Muse Spark 1.3 — Muse Spark 1.3 lists deepSWE v1.1 long-horizon software engineering (75.4) among its strengths; Hunyuan Hy4 Preview does not.
Near-perfect long-context retrieval (MRCR v2 512K-1M: 98.1): Muse Spark 1.3 — Muse Spark 1.3 lists near-perfect long-context retrieval (MRCR v2 512K-1M: 98.1) among its strengths; Hunyuan Hy4 Preview does not.
Lowest cost at scale: Hunyuan Hy4 Preview — At $0.834/$2.501 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Which should you pick?
A cost-sensitive startup shipping high volume: Hunyuan Hy4 Preview — At $0.834/$2.501 per 1M tokens it undercuts Muse Spark 1.3, and on millions of tokens that margin decides the monthly bill.
A team with data-privacy or self-hosting needs: Hunyuan Hy4 Preview — Open weights let you run it on your own hardware; Muse Spark 1.3 is API-only.
Anyone whose priority is gpqa diamond (92.3): Hunyuan Hy4 Preview — It is specifically built for that.
Anyone whose priority is agentic coding with ~20% fewer tool calls and ~25% fewer tokens than muse spark 1.2: Muse Spark 1.3 — That is its strongest area.
An enterprise with regional data-residency rules: Muse Spark 1.3 or Hunyuan Hy4 Preview — Origin (China vs US) affects where data is processed and which compliance regime applies — check the provider's terms for your region.
Hunyuan Hy4 Preview: where it fits
Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline. Released August 28, 2026 by Tencent, it is built for gPQA Diamond (92.3), terminal-Bench (85.4), sWE-bench Multilingual (82.9), and large jump in long-horizon coding vs prior Hunyuan model (DeepSWE 28.0 to 64.3).
Its trade-offs are real: text-only, no native vision support, labeled a 'preview', not yet Tencent's finalized GA flagship, and sWE-Marathon score still low in absolute terms (31.9) despite a large relative jump. At $0.834 in / $2.501 out per million tokens, it sits in the budget price band.
Muse Spark 1.3: where it fits
Meta's September 2, 2026 agentic-coding model update, cutting tool calls and token usage versus Muse Spark 1.2 while its highest-reasoning mode remains gated for safety review. Released September 2, 2026 by Meta, it is built for agentic coding with ~20% fewer tool calls and ~25% fewer tokens than Muse Spark 1.2, deepSWE v1.1 long-horizon software engineering (75.4), near-perfect long-context retrieval (MRCR v2 512K-1M: 98.1), and ranks third overall on the Artificial Analysis Intelligence Index (score 61, xhigh variant; the limited-preview max variant scores 62) - behind only Claude Fable 5.1 and Claude Opus 5.
Its trade-offs: strongest 'max' reasoning configuration still gated pending additional safety testing, not yet open-weight, despite Meta roadmapping a future Muse Spark weights release, and no official SWE-bench Verified score published. At $1.25 in / $4.25 out per million tokens, it sits in the mid price band.
The bottom line for this matchup
The defining split here is open vs. closed. Hunyuan Hy4 Preview gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Muse Spark 1.3 gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Frequently asked questions
Is Hunyuan Hy4 Preview or Muse Spark 1.3 better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Hunyuan Hy4 Preview leans toward gpqa diamond (92.3) while Muse Spark 1.3 leans toward agentic coding with ~20% fewer tool calls and ~25% fewer tokens than muse spark 1.2, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Hunyuan Hy4 Preview or Muse Spark 1.3?
Hunyuan Hy4 Preview is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Muse Spark 1.3 is API-metered at $1.25/$4.25 per 1M tokens. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
Which has the bigger context window?
Both advertise 1M+ tokens (~1,500 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.
Can I use both Hunyuan Hy4 Preview and Muse Spark 1.3 together?
Yes — a multi-model platform like LumiChats gives you Hunyuan Hy4 Preview, Muse Spark 1.3 and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, Hunyuan Hy4 Preview or Muse Spark 1.3?
Muse Spark 1.3 — released September 2, 2026, about 5 days after Hunyuan Hy4 Preview.
Hunyuan Hy4 Preview vs Muse Spark 1.3
Tencent · China | Meta · US · Updated June 2026
Quick verdict
Pick Hunyuan Hy4 Preview for gpqa diamond (92.3) or terminal-bench (85.4). Pick Muse Spark 1.3 for agentic coding with ~20% fewer tool calls and ~25% fewer tokens than muse spark 1.2 or deepswe v1.1 long-horizon software engineering (75.4). Choose Hunyuan Hy4 Preview if you need self-hosting or data privacy; Muse Spark 1.3 if you want a managed API.
Hunyuan Hy4 Preview (Tencent, China) and Muse Spark 1.3 (Meta, US) line up two different AI ecosystems against each other — a comparison that is as much about cost philosophy and openness as raw capability. Hunyuan Hy4 Preview is tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline. Muse Spark 1.3 is meta's September 2, 2026 agentic-coding model update, cutting tool calls and token usage versus Muse Spark 1.2 while its highest-reasoning mode remains gated for safety review. They diverge most on price and open vs. closed weights — each quantified below from the models' real specs.
Key differences at a glance
▸Price: Hunyuan Hy4 Preview is about 1.5× cheaper on input ($0.834/$2.501 per 1M tokens vs $1.25/$4.25 per 1M tokens) — modest, but it adds up at steady volume.
▸Context window: both advertise 1M+ tokens (~1,500 pages). Tie on paper — test on your own long inputs, since usable recall varies by model.
▸Ecosystem: this is a China-vs-US matchup — they differ in pricing philosophy, data-residency options, and tooling ecosystems, not only benchmarks.
Side-by-side specs
Spec
Hunyuan Hy4 Preview
Muse Spark 1.3
Provider
Tencent (China)
Meta (US)
Released
August 28, 2026
September 2, 2026
Context window
1M+ tokens (~1,500 pages)
1M tokens (~1,500 pages)
Price (in/out)
$0.834/$2.501 per 1M tokens
$1.25/$4.25 per 1M tokens
Open weight?
Yes — self-hostable
No — API only
Modalities
text
text, image, video
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
98.1%
Who wins what
GPQA Diamond (92.3)
Hunyuan Hy4 Preview
Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline — and it runs cheaper at $0.834/$2.501 per 1M tokens.
Terminal-Bench (85.4)
Hunyuan Hy4 Preview
Muse Spark 1.3 is comparatively weak here — no official SWE-bench Verified score published
SWE-bench Multilingual (82.9)
Hunyuan Hy4 Preview
Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline — and its weights are open while Muse Spark 1.3 is API-only.
Agentic coding with ~20% fewer tool calls and ~25% fewer tokens than Muse Spark 1.2
Muse Spark 1.3
Meta's September 2, 2026 agentic-coding model update, cutting tool calls and token usage versus Muse Spark 1.2 while its highest-reasoning mode remains gated for safety review — and it is the newer of the two.
Muse Spark 1.3 lists near-perfect long-context retrieval (MRCR v2 512K-1M: 98.1) among its strengths; Hunyuan Hy4 Preview does not.
Lowest cost at scale
Hunyuan Hy4 Preview
At $0.834/$2.501 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Which should you pick?
A cost-sensitive startup shipping high volume
→ Hunyuan Hy4 Preview
At $0.834/$2.501 per 1M tokens it undercuts Muse Spark 1.3, and on millions of tokens that margin decides the monthly bill.
A team with data-privacy or self-hosting needs
→ Hunyuan Hy4 Preview
Open weights let you run it on your own hardware; Muse Spark 1.3 is API-only.
Anyone whose priority is gpqa diamond (92.3)
→ Hunyuan Hy4 Preview
It is specifically built for that.
Anyone whose priority is agentic coding with ~20% fewer tool calls and ~25% fewer tokens than muse spark 1.2
→ Muse Spark 1.3
That is its strongest area.
An enterprise with regional data-residency rules
→ Muse Spark 1.3 or Hunyuan Hy4 Preview
Origin (China vs US) affects where data is processed and which compliance regime applies — check the provider's terms for your region.
Hunyuan Hy4 Preview: where it fits
Tencent's open-sourced (Apache 2.0) next-generation Hunyuan flagship preview, released August 28, 2026 as a 770B-parameter (49B active) MoE model that helped optimize its own training pipeline. Released August 28, 2026 by Tencent, it is built for gPQA Diamond (92.3), terminal-Bench (85.4), sWE-bench Multilingual (82.9), and large jump in long-horizon coding vs prior Hunyuan model (DeepSWE 28.0 to 64.3).
Its trade-offs are real: text-only, no native vision support, labeled a 'preview', not yet Tencent's finalized GA flagship, and sWE-Marathon score still low in absolute terms (31.9) despite a large relative jump. At $0.834 in / $2.501 out per million tokens, it sits in the budget price band.
Muse Spark 1.3: where it fits
Meta's September 2, 2026 agentic-coding model update, cutting tool calls and token usage versus Muse Spark 1.2 while its highest-reasoning mode remains gated for safety review. Released September 2, 2026 by Meta, it is built for agentic coding with ~20% fewer tool calls and ~25% fewer tokens than Muse Spark 1.2, deepSWE v1.1 long-horizon software engineering (75.4), near-perfect long-context retrieval (MRCR v2 512K-1M: 98.1), and ranks third overall on the Artificial Analysis Intelligence Index (score 61, xhigh variant; the limited-preview max variant scores 62) - behind only Claude Fable 5.1 and Claude Opus 5.
Its trade-offs: strongest 'max' reasoning configuration still gated pending additional safety testing, not yet open-weight, despite Meta roadmapping a future Muse Spark weights release, and no official SWE-bench Verified score published. At $1.25 in / $4.25 out per million tokens, it sits in the mid price band.
The bottom line for this matchup
The defining split here is open vs. closed. Hunyuan Hy4 Preview gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Muse Spark 1.3 gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Want both Hunyuan Hy4 Preview and Muse Spark 1.3 without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.
Is Hunyuan Hy4 Preview or Muse Spark 1.3 better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Hunyuan Hy4 Preview leans toward gpqa diamond (92.3) while Muse Spark 1.3 leans toward agentic coding with ~20% fewer tool calls and ~25% fewer tokens than muse spark 1.2, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Hunyuan Hy4 Preview or Muse Spark 1.3?
Hunyuan Hy4 Preview is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Muse Spark 1.3 is API-metered at $1.25/$4.25 per 1M tokens. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
Which has the bigger context window?
Both advertise 1M+ tokens (~1,500 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.
Can I use both Hunyuan Hy4 Preview and Muse Spark 1.3 together?
Yes — a multi-model platform like LumiChats gives you Hunyuan Hy4 Preview, Muse Spark 1.3 and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, Hunyuan Hy4 Preview or Muse Spark 1.3?
Muse Spark 1.3 — released September 2, 2026, about 5 days after Hunyuan Hy4 Preview.
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.