GLM-5 (Reasoning) 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

GLM-5 (Reasoning)· Sarvam 105B

Quick Verdict

Pick GLM-5 (Reasoning) if you want the stronger benchmark profile. Sarvam 105B only becomes the better choice if knowledge is the priority.

GLM-5 (Reasoning) is clearly ahead on the aggregate, 82 to 60. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GLM-5 (Reasoning)'s sharpest advantage is in agentic, where it averages 78.3 against 49.5. The single biggest benchmark swing on the page is BrowseComp, 80% to 49.5%. Sarvam 105B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

GLM-5 (Reasoning) gives you the larger context window at 200K, compared with 128K for Sarvam 105B.

Operational tradeoffs

PriceFree*Free*
SpeedN/AN/A
TTFTN/AN/A
Context200K128K

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.

BenchmarkGLM-5 (Reasoning)Sarvam 105B
AgenticGLM-5 (Reasoning) wins
Terminal-Bench 2.081%
BrowseComp80%49.5%
OSWorld-Verified74%
CodingGLM-5 (Reasoning) wins
HumanEval88%
SWE-bench Verified62%45%
LiveCodeBench v671.7%
Multimodal & Grounded
MMMU-Pro74%
OfficeQA Pro84%
Reasoning
MuSR90%
BBH91%
gpqaDiamond78.7%
hle11.2%
KnowledgeSarvam 105B wins
MMLU96%90.6%
GPQA94%
SuperGPQA92%
MMLU-Pro81%81.7%
HLE29%
FrontierScience83%
SimpleQA92%
Instruction Following
IFEval84.8%
Multilingual
MGSM89%
MathematicsGLM-5 (Reasoning) wins
AIME 202398%
AIME 202499%
AIME 202598%88.3%
HMMT Feb 202394%
HMMT Feb 202496%
HMMT Feb 202595%
BRUMO 202596%
MATH-50092%98.6%
HMMT Feb 202585.8%
HMMT Nov 202585.8%
Frequently Asked Questions (5)

Which is better, GLM-5 (Reasoning) or Sarvam 105B?

GLM-5 (Reasoning) is ahead overall, 82 to 60. The biggest single separator in this matchup is BrowseComp, where the scores are 80% and 49.5%.

Which is better for knowledge tasks, GLM-5 (Reasoning) or Sarvam 105B?

Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 73.7. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, GLM-5 (Reasoning) or Sarvam 105B?

GLM-5 (Reasoning) has the edge for coding in this comparison, averaging 62 versus 45. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, GLM-5 (Reasoning) or Sarvam 105B?

GLM-5 (Reasoning) has the edge for math in this comparison, averaging 95.8 versus 92.3. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GLM-5 (Reasoning) or Sarvam 105B?

GLM-5 (Reasoning) has the edge for agentic tasks in this comparison, averaging 78.3 versus 49.5. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

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.