Pick Laguna XS 2.1 for remarkable efficiency — 70.9% on swe-bench verified from only 3b active parameters or open weights under openmdw-1.1, shipped day one in bf16, fp8, nvfp4 and int4 across every major runtime. Pick NVIDIA Nemotron 3 Super for high-throughput agentic reasoning (up to 2.2x gpt-oss-120b) or 1m-token context with strong long-context retrieval (91.6% ruler @ 1m). On a tight budget at scale, NVIDIA Nemotron 3 Super is the value pick.
Laguna XS 2.1 (Poolside) and NVIDIA Nemotron 3 Super (NVIDIA) are two of the models people most often weigh against each other in 2026. Laguna XS 2.1 is a 33B open-weight coding MoE running on 3B active parameters — 70.9% SWE-Bench Verified and very cheap, but unproven. NVIDIA Nemotron 3 Super is nVIDIA's open 120B-total/12B-active hybrid Mamba-Transformer MoE built for high-throughput agentic reasoning at 1M-token context. They diverge most on price, context window and coding benchmarks — each quantified below from the models' real specs.
Key differences
Context window: NVIDIA Nemotron 3 Super holds 3.8× more — 1M (~1,500 pages) vs 256K (~393 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
Coding: Laguna XS 2.1 leads SWE-Bench Verified by 10.4 points (70.9% vs 60.47%) — a real edge on hard, real-world software tasks.
Recency: Laguna XS 2.1 is the newer model by about 4 months (released July 2, 2026), usually meaning fresher training data and capabilities.
Specifications
Spec
Laguna XS 2.1
NVIDIA Nemotron 3 Super
Provider
Poolside (US)
NVIDIA (US)
Released
July 2, 2026
March 11, 2026
Context window
256K (~393 pages)
1M (~1,500 pages)
Price (in/out)
$0.1/$0.2 per 1M tokens
Open weight (self-host / free)
Open weight?
Yes — self-hostable
Yes — self-hostable
Modalities
text, code
text, code
SWE-Bench Verified
70.9%
60.47%
MRCR v2 @ 1M
Not published
Not published
Who wins what
Remarkable efficiency — 70.9% on SWE-Bench Verified from only 3B active parameters: Laguna XS 2.1 — It scores 70.9% on SWE-Bench Verified against NVIDIA Nemotron 3 Super's 60.47% — a 10.4-point edge on real repository work.
Open weights under OpenMDW-1.1, shipped day one in BF16, FP8, NVFP4 and INT4 across every major runtime: Laguna XS 2.1 — A 33B open-weight coding MoE running on 3B active parameters — 70.9% SWE-Bench Verified and very cheap, but unproven — and it leads SWE-Bench Verified 70.9% to 60.47%.
Cheap even on the paid tier, at roughly a sixth of GLM 4.7's input price: Laguna XS 2.1 — NVIDIA Nemotron 3 Super is comparatively weak here — text-only; no image, audio, or video input
High-throughput agentic reasoning (up to 2.2x GPT-OSS-120B): NVIDIA Nemotron 3 Super — Laguna XS 2.1 is comparatively weak here — weak on harder agentic work (37.5 on Terminal-Bench 2.0), and its gain over XS.2 is barely above noise
1M-token context with strong long-context retrieval (91.6% RULER @ 1M): NVIDIA Nemotron 3 Super — Its 1M window holds about 3.8× more than Laguna XS 2.1's 256K in a single prompt.
Strong math reasoning (90.21% AIME 2025): NVIDIA Nemotron 3 Super — NVIDIA's open 120B-total/12B-active hybrid Mamba-Transformer MoE built for high-throughput agentic reasoning at 1M-token context — and it carries the larger 1M context.
Lowest cost at scale: NVIDIA Nemotron 3 Super — Its weights are open, so at volume you pay for your own hardware instead of Laguna XS 2.1's $0.1/$0.2 per 1M tokens.
Largest single-prompt input: NVIDIA Nemotron 3 Super — Its 1M window is about 3.8× larger than Laguna XS 2.1's 256K, fitting roughly 1,500 pages in one prompt.
Which should you pick?
A cost-sensitive startup shipping high volume: NVIDIA Nemotron 3 Super — At Open weight (self-host / free) it undercuts Laguna XS 2.1, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases: NVIDIA Nemotron 3 Super — Larger 1M window fits more in one prompt.
Anyone whose priority is remarkable efficiency — 70.9% on swe-bench verified from only 3b active parameters: Laguna XS 2.1 — It is specifically built for that.
Anyone whose priority is high-throughput agentic reasoning (up to 2.2x gpt-oss-120b): NVIDIA Nemotron 3 Super — That is its strongest area.
Laguna XS 2.1: where it fits
A 33B open-weight coding MoE running on 3B active parameters — 70.9% SWE-Bench Verified and very cheap, but unproven. Released July 2, 2026 by Poolside, it is built for remarkable efficiency — 70.9% on SWE-Bench Verified from only 3B active parameters, open weights under OpenMDW-1.1, shipped day one in BF16, FP8, NVFP4 and INT4 across every major runtime, cheap even on the paid tier, at roughly a sixth of GLM 4.7's input price, and unusually transparent evaluation — it publishes its harness, step limits, and sandbox specs.
Its trade-offs are real: weeks old with no independent replication; every published score traces back to Poolside's own harness, the free endpoint trains on your inputs and outputs — disqualifying for proprietary code, which is its main use case, and weak on harder agentic work (37.5 on Terminal-Bench 2.0), and its gain over XS.2 is barely above noise. At $0.1 in / $0.2 out per million tokens, it sits in the budget price band.
NVIDIA Nemotron 3 Super: where it fits
NVIDIA's open 120B-total/12B-active hybrid Mamba-Transformer MoE built for high-throughput agentic reasoning at 1M-token context. Released March 11, 2026 by NVIDIA, it is built for high-throughput agentic reasoning (up to 2.2x GPT-OSS-120B), 1M-token context with strong long-context retrieval (91.6% RULER @ 1M), strong math reasoning (90.21% AIME 2025), and fully open weights, datasets, and recipes for self-hosting.
Its trade-offs: text-only; no image, audio, or video input, and requires roughly 8x H100-80GB GPUs to self-host at BF16. As an open-weight model, its running cost is your own hardware rather than a per-token fee.
The bottom line for this matchup
Laguna XS 2.1 and NVIDIA Nemotron 3 Super overlap enough that the right pick depends on your specific job. NVIDIA Nemotron 3 Super costs less per token; NVIDIA Nemotron 3 Super holds the larger context; and each leads in its own area — Laguna XS 2.1 for remarkable efficiency — 70.9% on swe-bench verified from only 3b active parameters, NVIDIA Nemotron 3 Super for high-throughput agentic reasoning (up to 2.2x gpt-oss-120b). Rather than crowning one, run the same hard task through both once and let the results decide.
Frequently asked questions
Is Laguna XS 2.1 or NVIDIA Nemotron 3 Super better for coding?
On SWE-Bench Verified, Laguna XS 2.1 scores 70.9% and NVIDIA Nemotron 3 Super scores 60.47% — Laguna XS 2.1 has the measurable edge.
Which is cheaper, Laguna XS 2.1 or NVIDIA Nemotron 3 Super?
NVIDIA Nemotron 3 Super is cheaper — $0.1/$0.2 per 1M tokens vs Open weight (self-host / free).
Which has the bigger context window?
NVIDIA Nemotron 3 Super — 1M vs 256K, about 3.8× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both Laguna XS 2.1 and NVIDIA Nemotron 3 Super together?
Yes — a multi-model platform like LumiChats gives you Laguna XS 2.1, NVIDIA Nemotron 3 Super 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, Laguna XS 2.1 or NVIDIA Nemotron 3 Super?
Laguna XS 2.1 — released July 2, 2026, about 4 months after NVIDIA Nemotron 3 Super.
Laguna XS 2.1 vs NVIDIA Nemotron 3 Super
Poolside · US | NVIDIA · US · Updated June 2026
Quick verdict
Pick Laguna XS 2.1 for remarkable efficiency — 70.9% on swe-bench verified from only 3b active parameters or open weights under openmdw-1.1, shipped day one in bf16, fp8, nvfp4 and int4 across every major runtime. Pick NVIDIA Nemotron 3 Super for high-throughput agentic reasoning (up to 2.2x gpt-oss-120b) or 1m-token context with strong long-context retrieval (91.6% ruler @ 1m). On a tight budget at scale, NVIDIA Nemotron 3 Super is the value pick.
Laguna XS 2.1 (Poolside) and NVIDIA Nemotron 3 Super (NVIDIA) are two of the models people most often weigh against each other in 2026. Laguna XS 2.1 is a 33B open-weight coding MoE running on 3B active parameters — 70.9% SWE-Bench Verified and very cheap, but unproven. NVIDIA Nemotron 3 Super is nVIDIA's open 120B-total/12B-active hybrid Mamba-Transformer MoE built for high-throughput agentic reasoning at 1M-token context. They diverge most on price, context window and coding benchmarks — each quantified below from the models' real specs.
Key differences at a glance
▸Context window: NVIDIA Nemotron 3 Super holds 3.8× more — 1M (~1,500 pages) vs 256K (~393 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
▸Coding: Laguna XS 2.1 leads SWE-Bench Verified by 10.4 points (70.9% vs 60.47%) — a real edge on hard, real-world software tasks.
▸Recency: Laguna XS 2.1 is the newer model by about 4 months (released July 2, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
Spec
Laguna XS 2.1
NVIDIA Nemotron 3 Super
Provider
Poolside (US)
NVIDIA (US)
Released
July 2, 2026
March 11, 2026
Context window
256K (~393 pages)
1M (~1,500 pages)
Price (in/out)
$0.1/$0.2 per 1M tokens
Open weight (self-host / free)
Open weight?
Yes — self-hostable
Yes — self-hostable
Modalities
text, code
text, code
SWE-Bench Verified
70.9%
60.47%
MRCR v2 @ 1M
Not published
Not published
Who wins what
Remarkable efficiency — 70.9% on SWE-Bench Verified from only 3B active parameters
Laguna XS 2.1
It scores 70.9% on SWE-Bench Verified against NVIDIA Nemotron 3 Super's 60.47% — a 10.4-point edge on real repository work.
Open weights under OpenMDW-1.1, shipped day one in BF16, FP8, NVFP4 and INT4 across every major runtime
Laguna XS 2.1
A 33B open-weight coding MoE running on 3B active parameters — 70.9% SWE-Bench Verified and very cheap, but unproven — and it leads SWE-Bench Verified 70.9% to 60.47%.
Cheap even on the paid tier, at roughly a sixth of GLM 4.7's input price
Laguna XS 2.1
NVIDIA Nemotron 3 Super is comparatively weak here — text-only; no image, audio, or video input
High-throughput agentic reasoning (up to 2.2x GPT-OSS-120B)
NVIDIA Nemotron 3 Super
Laguna XS 2.1 is comparatively weak here — weak on harder agentic work (37.5 on Terminal-Bench 2.0), and its gain over XS.2 is barely above noise
1M-token context with strong long-context retrieval (91.6% RULER @ 1M)
NVIDIA Nemotron 3 Super
Its 1M window holds about 3.8× more than Laguna XS 2.1's 256K in a single prompt.
Strong math reasoning (90.21% AIME 2025)
NVIDIA Nemotron 3 Super
NVIDIA's open 120B-total/12B-active hybrid Mamba-Transformer MoE built for high-throughput agentic reasoning at 1M-token context — and it carries the larger 1M context.
Lowest cost at scale
NVIDIA Nemotron 3 Super
Its weights are open, so at volume you pay for your own hardware instead of Laguna XS 2.1's $0.1/$0.2 per 1M tokens.
Largest single-prompt input
NVIDIA Nemotron 3 Super
Its 1M window is about 3.8× larger than Laguna XS 2.1's 256K, fitting roughly 1,500 pages in one prompt.
Which should you pick?
A cost-sensitive startup shipping high volume
→ NVIDIA Nemotron 3 Super
At Open weight (self-host / free) it undercuts Laguna XS 2.1, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases
→ NVIDIA Nemotron 3 Super
Larger 1M window fits more in one prompt.
Anyone whose priority is remarkable efficiency — 70.9% on swe-bench verified from only 3b active parameters
→ Laguna XS 2.1
It is specifically built for that.
Anyone whose priority is high-throughput agentic reasoning (up to 2.2x gpt-oss-120b)
→ NVIDIA Nemotron 3 Super
That is its strongest area.
Laguna XS 2.1: where it fits
A 33B open-weight coding MoE running on 3B active parameters — 70.9% SWE-Bench Verified and very cheap, but unproven. Released July 2, 2026 by Poolside, it is built for remarkable efficiency — 70.9% on SWE-Bench Verified from only 3B active parameters, open weights under OpenMDW-1.1, shipped day one in BF16, FP8, NVFP4 and INT4 across every major runtime, cheap even on the paid tier, at roughly a sixth of GLM 4.7's input price, and unusually transparent evaluation — it publishes its harness, step limits, and sandbox specs.
Its trade-offs are real: weeks old with no independent replication; every published score traces back to Poolside's own harness, the free endpoint trains on your inputs and outputs — disqualifying for proprietary code, which is its main use case, and weak on harder agentic work (37.5 on Terminal-Bench 2.0), and its gain over XS.2 is barely above noise. At $0.1 in / $0.2 out per million tokens, it sits in the budget price band.
NVIDIA Nemotron 3 Super: where it fits
NVIDIA's open 120B-total/12B-active hybrid Mamba-Transformer MoE built for high-throughput agentic reasoning at 1M-token context. Released March 11, 2026 by NVIDIA, it is built for high-throughput agentic reasoning (up to 2.2x GPT-OSS-120B), 1M-token context with strong long-context retrieval (91.6% RULER @ 1M), strong math reasoning (90.21% AIME 2025), and fully open weights, datasets, and recipes for self-hosting.
Its trade-offs: text-only; no image, audio, or video input, and requires roughly 8x H100-80GB GPUs to self-host at BF16. As an open-weight model, its running cost is your own hardware rather than a per-token fee.
The bottom line for this matchup
Laguna XS 2.1 and NVIDIA Nemotron 3 Super overlap enough that the right pick depends on your specific job. NVIDIA Nemotron 3 Super costs less per token; NVIDIA Nemotron 3 Super holds the larger context; and each leads in its own area — Laguna XS 2.1 for remarkable efficiency — 70.9% on swe-bench verified from only 3b active parameters, NVIDIA Nemotron 3 Super for high-throughput agentic reasoning (up to 2.2x gpt-oss-120b). Rather than crowning one, run the same hard task through both once and let the results decide.
Want both Laguna XS 2.1 and NVIDIA Nemotron 3 Super 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 Laguna XS 2.1 or NVIDIA Nemotron 3 Super better for coding?
On SWE-Bench Verified, Laguna XS 2.1 scores 70.9% and NVIDIA Nemotron 3 Super scores 60.47% — Laguna XS 2.1 has the measurable edge.
Which is cheaper, Laguna XS 2.1 or NVIDIA Nemotron 3 Super?
NVIDIA Nemotron 3 Super is cheaper — $0.1/$0.2 per 1M tokens vs Open weight (self-host / free).
Which has the bigger context window?
NVIDIA Nemotron 3 Super — 1M vs 256K, about 3.8× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both Laguna XS 2.1 and NVIDIA Nemotron 3 Super together?
Yes — a multi-model platform like LumiChats gives you Laguna XS 2.1, NVIDIA Nemotron 3 Super 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, Laguna XS 2.1 or NVIDIA Nemotron 3 Super?
Laguna XS 2.1 — released July 2, 2026, about 4 months after NVIDIA Nemotron 3 Super.
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.