GPT-5.4 nano vs Sarvam 105B

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

Agentic
Coding
Multimodal & Grounded
Reasoning
Knowledge
Instruction Following
Multilingual
Mathematics

GPT-5.4 nano· Sarvam 105B

Quick Verdict

Pick Sarvam 105B if you want the stronger benchmark profile. GPT-5.4 nano only becomes the better choice if coding is the priority or you need the larger 400K context window.

Sarvam 105B has the cleaner overall profile here, landing at 60 versus 58. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Sarvam 105B's sharpest advantage is in knowledge, where it averages 81.7 against 53.2. GPT-5.4 nano does hit back in coding, so the answer changes if that is the part of the workload you care about most.

GPT-5.4 nano is also the more expensive model on tokens at $0.20 input / $1.25 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Sarvam 105B. That is roughly Infinityx on output cost alone. GPT-5.4 nano gives you the larger context window at 400K, compared with 128K for Sarvam 105B.

Operational tradeoffs

ProviderOpenAISarvam
Price$0.20 / $1.25Free*
Speed191 t/sN/A
TTFT3.64sN/A
Context400K128K

Decision framing

BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.

Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.

BenchmarkGPT-5.4 nanoSarvam 105B
AgenticSarvam 105B wins
Terminal-Bench 2.046.3%
OSWorld-Verified39%
MCP Atlas56.1%
Toolathlon35.5%
Tau2-Telecom92.5%
BrowseComp49.5%
CodingGPT-5.4 nano wins
SWE-bench Pro52.4%
LiveCodeBench v671.7%
SWE-bench Verified45%
Multimodal & Grounded
MMMU-Pro66.1%
MMMU-Pro w/ Python69.5%
Reasoning
MRCRv238.7%
MRCR v2 64K-128K44.2%
MRCR v2 128K-256K33.1%
Graphwalks BFS 128K73.4%
Graphwalks Parents 128K50.8%
gpqaDiamond78.7%
hle11.2%
KnowledgeSarvam 105B wins
GPQA82.8%
HLE37.7%
HLE w/o tools24.3%
MMLU90.6%
MMLU-Pro81.7%
Instruction Following
IFEval84.8%
Multilingual
Coming soon
Mathematics
MATH-50098.6%
AIME 202588.3%
HMMT Feb 202585.8%
HMMT Nov 202585.8%
Frequently Asked Questions (4)

Which is better, GPT-5.4 nano or Sarvam 105B?

Sarvam 105B is ahead overall, 60 to 58.

Which is better for knowledge tasks, GPT-5.4 nano or Sarvam 105B?

Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 53.2. GPT-5.4 nano stays close enough that the answer can still flip depending on your workload.

Which is better for coding, GPT-5.4 nano or Sarvam 105B?

GPT-5.4 nano has the edge for coding in this comparison, averaging 52.4 versus 45. Sarvam 105B stays close enough that the answer can still flip depending on your workload.

Which is better for agentic tasks, GPT-5.4 nano or Sarvam 105B?

Sarvam 105B has the edge for agentic tasks in this comparison, averaging 49.5 versus 42.9. GPT-5.4 nano stays close enough that the answer can still flip depending on your workload.

Last updated: April 3, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.